International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015 DOI : 10.5121/ijp2p.2015.6201 1 CONGESTION CONTROL FOR P2P LIVE STREAMING
In recent years, research efforts tried to exploit peer-to-peer (P2P) systems in order to provide Live
Streaming (LS) and Video-on-Demand (VoD) services. Most of these research efforts focus on the
development of distributed P2P block schedulers for content exchange among the participating peers and
on the characteristics of the overlay graph (P2P overlay) that interconnects the set of these peers.
Currently, researchers try to combine peer-to-peer systems with cloud infrastructures. They developed
monitoring and control architectures that use resources from the cloud in order to enhance QoS and
achieve an attractive trade-off between stability and low cost operation. However, there is a lack of
research effort on the congestion control of these systems and the existing congestion control architectures
are not suitable for P2P live streaming traffic (small sequential non persistent traffic towards multiple
network locations). This paper proposes a P2P live streaming traffic aware congestion control protocol
that: i) is capable to manage sequential traffic heading to multiple network destinations , ii) efficiently
exploits the available bandwidth, iii) accurately measures the idle peer resources, iv) avoids network
congestion, and v) is friendly to traditional TCP generated traffic. The proposed P2P congestion control
has been implemented, tested and evaluated through a series of real experiments powered across the
BonFIRE infrastructure
QOS - LIQUIDSTREAM: SCALABLE MONITORING AND BANDWIDTH CONTROL IN PEER TO PEER...ijp2p
The vast majority of research in P2P live streaming systems focuses on system architectures that offer to
participating peers: high upload bandwidth utilization, low delays during the video stream diffusion,
robustness and stability under dynamic network conditions and peers behavior. On the other hand in order
to guarantee the complete and on time video distribution to every participating peer, the average upload
bandwidth of the participating peers should be always greater than the playback rate of the video stream.
Most of the approaches do not take into consideration this requirement. Thus, in this paper we propose a
very scalable monitoring mechanism of the total upload bandwidth of the participating peers, which is
dynamic, accurate and with low overhead. Moreover, by exploiting this monitoring mechanism we present
and evaluate an algorithm that allows the accurate and on time estimation of the minimal required
additional bandwidth that an external set of resources (e.g. auxiliary peers) have to contribute. In this way
we guarantee the uninterrupted the stream delivery and provide high Quality of Service (QoS) in live
streaming.
This document provides summaries of 15 networking projects from TTA including the project code, title, description, and reference. The projects cover topics like delay analysis of opportunistic spectrum access MAC protocols, load balancing for network traffic measurement, key exchange protocols for parallel network file systems, anomaly detection in intrusion detection systems, and energy efficient group key agreement for wireless networks. The document provides contact information at the end for obtaining full project papers.
The Effect of Seeking Operation on QoE of HTTP Adaptive Streaming ServicesIJCNCJournal
In this paper, we assess multidimensional QoE (Quality of Experience) of HTTP-based streaming services
in seeking operation to evaluate the effect of two transmission schemes: adaptive bitrate streaming and
progressive download. We perform a subjective experiment with two contents and various network load
conditions. In the experiment, subjects find pre-specified scenes by means of seeking the video as they want
to see the scenes right now. We also perform the principal component analysis for the assessment result of
multidimensional QoE. We then find that the adaptive bitrate streaming is not necessarily effective for QoE
enhancement; the effectiveness of the scheme depends on the usage of the system and network conditions.
This document discusses two real-time streaming protocols - Real Time Streaming Protocol (RTSP) and Web Real-Time Communication (WebRTC). It presents a comparative study of these two protocols by developing new mobile applications that implement each protocol on Android. The applications are analyzed based on connection establishment time and stream reception time, which influence quality of service. The applications are also compared to popular video streaming apps to evaluate stream packet delay, with results showing the WebRTC implementation improves upon other apps.
A Proposal for End-to-End QoS Provisioning in Software-Defined NetworksIJECEIAES
This paper describes a framework application for the control plane of a network infras- tructure; the objective is to feature end-user applications with the capability of requesting at any time a customised end-to-end Quality-of-Service profile in the context of dynamic Service-Level-Agreements. Our solution targets current and future real-time applications that require tight QoS parameters, such as a guaranteed end-to-end delay bound. These applications include, but are not limited to, health-care, mobility, education, manufacturing, smart grids, gaming and much more. We discuss the issues related to the previous Integrated Service and the reason why the RSVP protocol for guaranteed QoS did not take off. Then we present a new signaling and resource reservation framework based on the cutting-edge network controller ONOS. Moreover, the presented system foresees the need of considering the edges of the network, where terminal applications are connected to, to be piloted by distinct logically centralised controllers. We discuss a possible inter-domain communication mechanism to achieve the end-to-end QoS guarantee.
This document summarizes a review paper on congestion control approaches for real-time streaming applications on the Internet. It discusses how TCP is not well-suited for real-time streaming due to its reliance on packet loss and variable bitrates. The paper reviews different end-to-end and active queue management approaches for congestion control that aim to reduce latency and jitter. It covers issues with single and shared bottlenecks on the Internet that can lead to congestion and the need for new transport protocols and congestion control for real-time media streaming.
MIPV6 PROTOCOLS: A SURVEY AND COMPARATIVE ANALYSIScscpconf
As the future generation networks are envisioned to be heterogeneous in nature, seamless
mobility in such networks is an important issue. While IETF work groups have standardized
various mobility management protocols, such as Mobile IPv6 (MIPv6), Fast Handovers for
Mobile IPv6 (Predictive FMIPv6, and Reactive FMIPv6), Hierarchical Mobile IPv6 (HMIPv6),
Proxy Mobile IPv6 (PMIPv6) and Fast Handovers for PMIPv6 (Predictive FPMIPv6, and
Reactive FPMIPv6), out of which some are host based and some are network based, the
decision regarding which protocol suits the future networks is still a research issue. The study
of various mobility management protocols in terms handover latency and the number of hops is
needed to evaluate these protocols. Even though much study has been done in literature in terms
of handover latency, study still needs performance evaluation in terms of average hop delay. In
this paper we study various mobility management protocols by applying simple numerical
analysis. The study is carried out for performance evaluation of various mobility management
protocols in terms of average hop delay, wireless link delay, wired part delay, and binding
update and registration delay. In this work, the average hop delay is estimated in terms of total
handover latency and total number of hops contributing to each protocol. The study enables us
to make a few important observations regarding the performance of these mobility management
Analysis of Link State Resource Reservation Protocol for Congestion Managemen...ijgca
With the wide spread of WiFi hotspots, concentrated traffic workload on Smart Web (SW) can slow down
the network performance. This paper presents a congestion management strategy considering real time
activities in today’s smart web. With the SW context, cooperative packet recovery using resource
reservation procedure for TCP flows was adapted for mitigating packet losses. This is to maintain data
consistency between various access points of smart web hotspot. Using a real world scenario, it was
confirmed that generic TCP cannot handle traffic congestion in a SW hotspot network. With TCP in
scalable workload environments, continuous packet drops at the event of congestion remains obvious. This
is unacceptable for mission critical domains. An enhanced Link State Resource Reservation Protocol (LSRSVP)
which serves as dynamic feedback mechanism in smart web hotspots is presented. The contextual
behaviour was contrasted with the generic TCP model. For the LS-RSVP, a simulation experiment for TCP
connection between servers at the remote core layer and the access layer was carried out while using
selected benchmark metrics. From the results, under realistic workloads, a steady-state throughput
response was achieved by TCP LS-RSVP to about 3650Bits/secs compared with generic TCP plots in a
previous study. Considering network service availability, this was found to be dependent on fault-tolerance
of the hotspot network. From study, a high peak threshold of 0.009 (i.e. 90%) was observed. This shows
fairly acceptable service availability behaviour compared with the existing TCP schemes. For packet drop
effects, an analysis on the network behaviour with respect to the LS-RSVP yielded a drop response of about
0.000106 bits/sec which is much lower compared with the case with generic TCP with over 0.38 bits/sec.
The latency profile of average FTP download response was found to be 0.030secs, but with that of FTP
upload response, this yielded about 0.028 sec. The results from the study demonstrate efficiency and
optimality for realistic loads in Smart web contexts.
QOS - LIQUIDSTREAM: SCALABLE MONITORING AND BANDWIDTH CONTROL IN PEER TO PEER...ijp2p
The vast majority of research in P2P live streaming systems focuses on system architectures that offer to
participating peers: high upload bandwidth utilization, low delays during the video stream diffusion,
robustness and stability under dynamic network conditions and peers behavior. On the other hand in order
to guarantee the complete and on time video distribution to every participating peer, the average upload
bandwidth of the participating peers should be always greater than the playback rate of the video stream.
Most of the approaches do not take into consideration this requirement. Thus, in this paper we propose a
very scalable monitoring mechanism of the total upload bandwidth of the participating peers, which is
dynamic, accurate and with low overhead. Moreover, by exploiting this monitoring mechanism we present
and evaluate an algorithm that allows the accurate and on time estimation of the minimal required
additional bandwidth that an external set of resources (e.g. auxiliary peers) have to contribute. In this way
we guarantee the uninterrupted the stream delivery and provide high Quality of Service (QoS) in live
streaming.
This document provides summaries of 15 networking projects from TTA including the project code, title, description, and reference. The projects cover topics like delay analysis of opportunistic spectrum access MAC protocols, load balancing for network traffic measurement, key exchange protocols for parallel network file systems, anomaly detection in intrusion detection systems, and energy efficient group key agreement for wireless networks. The document provides contact information at the end for obtaining full project papers.
The Effect of Seeking Operation on QoE of HTTP Adaptive Streaming ServicesIJCNCJournal
In this paper, we assess multidimensional QoE (Quality of Experience) of HTTP-based streaming services
in seeking operation to evaluate the effect of two transmission schemes: adaptive bitrate streaming and
progressive download. We perform a subjective experiment with two contents and various network load
conditions. In the experiment, subjects find pre-specified scenes by means of seeking the video as they want
to see the scenes right now. We also perform the principal component analysis for the assessment result of
multidimensional QoE. We then find that the adaptive bitrate streaming is not necessarily effective for QoE
enhancement; the effectiveness of the scheme depends on the usage of the system and network conditions.
This document discusses two real-time streaming protocols - Real Time Streaming Protocol (RTSP) and Web Real-Time Communication (WebRTC). It presents a comparative study of these two protocols by developing new mobile applications that implement each protocol on Android. The applications are analyzed based on connection establishment time and stream reception time, which influence quality of service. The applications are also compared to popular video streaming apps to evaluate stream packet delay, with results showing the WebRTC implementation improves upon other apps.
A Proposal for End-to-End QoS Provisioning in Software-Defined NetworksIJECEIAES
This paper describes a framework application for the control plane of a network infras- tructure; the objective is to feature end-user applications with the capability of requesting at any time a customised end-to-end Quality-of-Service profile in the context of dynamic Service-Level-Agreements. Our solution targets current and future real-time applications that require tight QoS parameters, such as a guaranteed end-to-end delay bound. These applications include, but are not limited to, health-care, mobility, education, manufacturing, smart grids, gaming and much more. We discuss the issues related to the previous Integrated Service and the reason why the RSVP protocol for guaranteed QoS did not take off. Then we present a new signaling and resource reservation framework based on the cutting-edge network controller ONOS. Moreover, the presented system foresees the need of considering the edges of the network, where terminal applications are connected to, to be piloted by distinct logically centralised controllers. We discuss a possible inter-domain communication mechanism to achieve the end-to-end QoS guarantee.
This document summarizes a review paper on congestion control approaches for real-time streaming applications on the Internet. It discusses how TCP is not well-suited for real-time streaming due to its reliance on packet loss and variable bitrates. The paper reviews different end-to-end and active queue management approaches for congestion control that aim to reduce latency and jitter. It covers issues with single and shared bottlenecks on the Internet that can lead to congestion and the need for new transport protocols and congestion control for real-time media streaming.
MIPV6 PROTOCOLS: A SURVEY AND COMPARATIVE ANALYSIScscpconf
As the future generation networks are envisioned to be heterogeneous in nature, seamless
mobility in such networks is an important issue. While IETF work groups have standardized
various mobility management protocols, such as Mobile IPv6 (MIPv6), Fast Handovers for
Mobile IPv6 (Predictive FMIPv6, and Reactive FMIPv6), Hierarchical Mobile IPv6 (HMIPv6),
Proxy Mobile IPv6 (PMIPv6) and Fast Handovers for PMIPv6 (Predictive FPMIPv6, and
Reactive FPMIPv6), out of which some are host based and some are network based, the
decision regarding which protocol suits the future networks is still a research issue. The study
of various mobility management protocols in terms handover latency and the number of hops is
needed to evaluate these protocols. Even though much study has been done in literature in terms
of handover latency, study still needs performance evaluation in terms of average hop delay. In
this paper we study various mobility management protocols by applying simple numerical
analysis. The study is carried out for performance evaluation of various mobility management
protocols in terms of average hop delay, wireless link delay, wired part delay, and binding
update and registration delay. In this work, the average hop delay is estimated in terms of total
handover latency and total number of hops contributing to each protocol. The study enables us
to make a few important observations regarding the performance of these mobility management
Analysis of Link State Resource Reservation Protocol for Congestion Managemen...ijgca
With the wide spread of WiFi hotspots, concentrated traffic workload on Smart Web (SW) can slow down
the network performance. This paper presents a congestion management strategy considering real time
activities in today’s smart web. With the SW context, cooperative packet recovery using resource
reservation procedure for TCP flows was adapted for mitigating packet losses. This is to maintain data
consistency between various access points of smart web hotspot. Using a real world scenario, it was
confirmed that generic TCP cannot handle traffic congestion in a SW hotspot network. With TCP in
scalable workload environments, continuous packet drops at the event of congestion remains obvious. This
is unacceptable for mission critical domains. An enhanced Link State Resource Reservation Protocol (LSRSVP)
which serves as dynamic feedback mechanism in smart web hotspots is presented. The contextual
behaviour was contrasted with the generic TCP model. For the LS-RSVP, a simulation experiment for TCP
connection between servers at the remote core layer and the access layer was carried out while using
selected benchmark metrics. From the results, under realistic workloads, a steady-state throughput
response was achieved by TCP LS-RSVP to about 3650Bits/secs compared with generic TCP plots in a
previous study. Considering network service availability, this was found to be dependent on fault-tolerance
of the hotspot network. From study, a high peak threshold of 0.009 (i.e. 90%) was observed. This shows
fairly acceptable service availability behaviour compared with the existing TCP schemes. For packet drop
effects, an analysis on the network behaviour with respect to the LS-RSVP yielded a drop response of about
0.000106 bits/sec which is much lower compared with the case with generic TCP with over 0.38 bits/sec.
The latency profile of average FTP download response was found to be 0.030secs, but with that of FTP
upload response, this yielded about 0.028 sec. The results from the study demonstrate efficiency and
optimality for realistic loads in Smart web contexts.
This document summarizes and evaluates scheduling algorithms for wireless IP networks that support multiclass traffic. It begins by describing the challenges of providing quality of service (QoS) over wireless networks due to time-varying transmission quality and location-dependent errors. It then reviews existing scheduling algorithms like weighted fair queuing (WFQ) and discusses their limitations in wireless environments. The document proposes a new scheduling mechanism that differentiates service between traffic classes and subclasses, allows compensation for non-real time traffic, and adjusts weights of real-time flows in error states to maintain throughput. Overall, the scheduling algorithm aims to provide QoS, fairness between flows, and flexibility to adapt to changing wireless channel conditions.
Experimental evaluation of scalability and reliability of a feedback based up...ijma
As a result of rapidly changing traffic characteristics in QoS-enabled networks oftentimes renegotiating
the bandwidth requirements are needed. Once renegotiation is started, the sender keeps this process of
invoking renegotiation until new requirements can be fulfilled (or until connection is eventually
terminated.) The frequency of polling the network is delicate balance between huge traffic overhead traffic
with decreased throughput and under-utilization of the network. While driving optimal follow-up rate is a
hard problem, several efficient solutions have been proposed. We have earlier proposed a Scalable
Feedback Based UPC-Parameters Renegotiation Protocol for ATM networks which gives efficient solution
to this problem. The proposed solution minimizes the overhead by shifting the repeated polling away from
the senders/users. Experimental evaluation of scalability and reliability aspects of our solution is presented
in this paper.
Fast Distribution of Replicated Content to Multi- Homed ClientsIDES Editor
Clients can potentially have access to more than
one communication network nowadays due to the availability
of a wide variety of access technologies. On the other hand,
service replication has become a trivial approach in overlay
networks to provide a high availability of data and better QoS.
In this paper, we consider such a multi-homed client seeking
a replicated service in overlay network (e.g., CDN, peer-topeer).
Our aim is to improve the content distribution by
proposing a new model for being applied at the applicationlevel
and in a fully distributed way. Basically, our model
proposes to determine the best mirror server that could be
reached through each client’s network interface based on
application utility function. Then, it consists of downloading
the requested content from the determined best servers
simultaneously through their associated interfaces. Each best
server should deliver a specific estimated range of bytes (i.e.,
content chunk) to an independent TCP socket opened at the
client side for being finally aggregated at the applicationlevel.
Our real experiments show that our model is able to
considerably improve the QoS (e.g., content transfer time)
perceived by the client comparing to the traditional content
distribution techniques.
Peer-to-Peer streaming technology has become one of the major Internet applications as it offers the opportunity of broadcasting high quality video content to a large number of peers with low costs. It is widely accepted that with the efficient utilization of peers and server's upload capacities, peers can enjoy watching a high bit rate video with minimal end-to-end delay. In this paper, we present a practical scheduling algorithm that works in the challenging condition where no spare capacity is available, i.e., it maximally utilizes the resources and broadcasts the maximum streaming rate. Each peer contacts with only a small number of neighbours in the overlay network and autonomously subscribes to sub-streams according to a budget-model in such a way that the number of peers forwarding exactly one sub-stream will be maximized. The hop-count delay is also taken into account to construct a short depth trees. Finally, we show through simulation that peers dynamically converge to an efficient overlay structure with a short hop-count delay. Moreover, the proposed scheme gives nice features in the homogeneous case and overcomes SplitStream in all simulated scenarios.
This document summarizes a study on the performance of LTE networks. The researchers conducted passive and active measurements on a commercial LTE network with over 300,000 users to analyze network characteristics and resource utilization. They found that while LTE provides higher bandwidth than 3G, TCP flows often underutilize available bandwidth due to factors like limited receive windows. On average, flows used only 52% of available bandwidth, lengthening transfers and wasting energy. The researchers developed techniques to estimate bandwidth and identify inefficient application behaviors to recommend protocol and design improvements.
QoS Oriented Coding For Mobility Constraint in Wireless Networksiosrjce
IOSR Journal of Electronics and Communication Engineering(IOSR-JECE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of electronics and communication engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in electronics and communication engineering. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
The document proposes a framework for maximizing the aggregate utility of traffic flows in a wireless mesh network while meeting minimum rate requirements and accounting for interference. It formulates the problem as an optimization that assigns transmission parameters like power, channels, and time slots. If minimum rates cannot be met for all flows, the framework intelligently rejects some flows and recalculates resource allocation. It aims to enhance quality of service support compared to prior work in wired networks by addressing self-interference challenges in wireless multi-hop networks.
Implementing a Session Aware Policy Based Mechanism for QoS Control in LTEIJERA Editor
Quality of Service (QoS) provisioning has become significant with the widely growth of multimedia applications and high increase in the number of users in both wireless and wired networks. In this paper, we implemented a session-aware policy based mechanism for QoS provisioning and control in LTE (Long Term Evolution) networks. Policies are a set of rules identifying the QoS parameters for users. Implementation included DiffServ (Differentiated Services) configuration and setting policies inside the PCRF (Policy Charging Rules Function) which is the brain entity in LTE, then mapping from QCI (QoS Class ID) to DiffServ. Moreover, the dialogue between PCEF (Policy Charging Enforcement Function) and PCRF was implemented. Simulations on four different traffic application types: VoIP (voice over IP), video, web, and ftp (file transfer protocol) were performed under the network simulator (ns2). Results showed that applying PCEF over the different traffic applications has a great effect in controlling these applications and specifically UDP (User Datagram Protocol) based applications such as video.
1 improvement of tcp congestion window over ltetanawan44
This document discusses improving the performance of TCP congestion control over LTE-Advanced networks. It proposes a new congestion avoidance mechanism that uses the available bandwidth of the connection to better detect the network path capacity and improve congestion avoidance. The mechanism is tested using the NS-2 network simulator to model LTE-Advanced traffic. The document provides background on LTE-Advanced network architecture and existing TCP congestion control mechanisms. It aims to develop an enhanced TCP variant that can efficiently transfer high data rates over the large bandwidth, low latency links of LTE-Advanced networks.
Enhanced Protocol for Wireless Content-Centric Network csandit
Recently, Content-Centric Networking (CCN) was intr
oduced and is expected as a new concept
of future internet architecture. Even though CCN is
initially studied for wired networks,
recently, it is also studied for wireless environme
nt. In this paper, we discuss improvement
method for efficient content flooding over wireless
CCNs. The proposed scheme of this paper
use MAC Address of nodes when Interest and Data Pac
ket are forwarded in order to limit the
area of flooding of packets. The proposed protocol
not only reduces the spread of Data packets,
but also offers priority of forwarding to nodes of
shortest path. As a consequence, it reduce
content download time which is proved by extensive
simulations.
Congestion control in packet switched wide area networks using a feedback modelijcses
In a complex world, where networking expands very rapidly, the network stability of flow of bandwidth
played a vital role in transmitting packets. Hence, it was imperative to find solution to the problem of
congestion especially in the follow of bandwidth stability.
Congestion in computer networking is caused by so many factors. Some of the signs are packet loss,
queuing delay resulting from overloading the buffer, faulty hardware devices, intermixing of old and new
technologies and unstable flow of bandwidth resulting from positive feedback
Practical active network services within content-aware gatewaysTal Lavian Ph.D.
The Internet has seen an increase in complexity due to the introduction of new types of networking devices and services, particularly at points of discontinuity known as network edges. As the networking industry continues to add revenue generating services at network edges, there is an increasing need to provide a systematic method for dynamically introducing and providing these new services in lieu of the ad-hoc approach that is in use today. To this end we support a phased approach to "activating" the Internet and suggest that there exists an immediate need for realizing Active Networks concepts at the network edges. In this context, we present our efforts towards the development of a Content-aware Active Gateway (CAG) architecture. With the help of two practical services running on our initial prototype, built from commercial networking devices, we give a qualitative and quantitative view of the CAG potential.
Traffic-aware adaptive server load balancing for softwaredefined networks IJECEIAES
Servers in data center networks handle heterogeneous bulk loads. Load balancing, therefore, plays an important role in optimizing network bandwidth and minimizing response time. A complete knowledge of the current network status is needed to provide a stable load in the network. The process of network status catalog in a traditional network needs additional processing which increases complexity, whereas, in software defined networking, the control plane monitors the overall working of the network continuously. Hence it is decided to propose an efficient load balancing algorithm that adapts SDN. This paper proposes an efficient algorithm TAASLB-traffic-aware adaptive server load balancing to balance the flows to the servers in a data center network. It works based on two parameters, residual bandwidth, and server capacity. It detects the elephant flows and forwards them towards the optimal server where it can be processed quickly. It has been tested with the Mininet simulator and gave considerably better results compared to the existing server load balancing algorithms in the floodlight controller. After experimentation and analysis, it is understood that the method provides comparatively better results than the existing load balancing algorithms.
This document discusses next generation internet over satellite networks. It covers new services and applications for internet integrated services, modeling elastic and inelastic traffic, quality of service provisioning, traffic modeling techniques, and statistical methods for modeling different types of traffic including renewal processes and Markov models. It also discusses traffic engineering principles, multi-protocol label switching, internet protocol version 6, and the future development of satellite networking.
The article looks into the current state of the art of dynamic routing protocols with respect to their
possibilities to react to changes in the Quality of Service when selecting the best route towards a
destination network. New options that could leverage information about the ever changing QoS parameters
for data communication are analysed and a Cisco Performance Routing solution is described more in
detail. The practical part of this work focuses on a design and implementation of a test bed that provides a
scalable laboratory architecture to manipulate QoS parameters of different data communications flowing
through it. The test bed is used in various use cases that were used to evaluate Cisco Performance Routing
optimization capabilities in different scenarios.
QOS - LIQUIDSTREAM: SCALABLE MONITORING AND BANDWIDTH CONTROL IN PEER TO PEER...ijp2p
The vast majority of research in P2P live streaming systems focuses on system architectures that offer to
participating peers: high upload bandwidth utilization, low delays during the video stream diffusion,
robustness and stability under dynamic network conditions and peers behavior. On the other hand in order
to guarantee the complete and on time video distribution to every participating peer, the average upload
bandwidth of the participating peers should be always greater than the playback rate of the video stream.
Most of the approaches do not take into consideration this requirement. Thus, in this paper we propose a
very scalable monitoring mechanism of the total upload bandwidth of the participating peers, which is
dynamic, accurate and with low overhead. Moreover, by exploiting this monitoring mechanism we present
and evaluate an algorithm that allows the accurate and on time estimation of the minimal required
additional bandwidth that an external set of resources (e.g. auxiliary peers) have to contribute. In this way
we guarantee the uninterrupted the stream delivery and provide high Quality of Service (QoS) in live
streaming.
A HYBRID PUSH-PULL OVERLAY NETWORK FOR PEER-TO-PEER VIDEO STREAMINGijp2p
In this paper, we have proposed a hybrid push-pull protocol for peer-to-peer live video streaming. The
main goal of this research is to minimize the network end-to-end delay in comparison to pure mesh
networks. Hybrid protocols, in most cases, suffer from complex construction and maintenance. Therefore,
our proposed protocol uses a pure mesh topology and a single layer video coding. In summary, our pushpull protocol has two parts. The pull-based part which is done on the mesh network, and the push-based
part which consists of two phases: parent selection and tree construction. When a push procedure appears,
it is very important to prevent data redundancy. To satisfy this condition, we have introduced a parent
selection method. In this method, by parent selection based on the minimum arrival time, the most stable
node will be selected. This node has the advantage of maximizing the expected service time of the tree.
Using this method, there is no need for maintaining any extra information and topology control data.
Finally, we do performance evaluation using OMNeT++ simulator. The simulation results show that the
proposed architecture has better performance in start-up delay, end-to-end delay, and distortion than pure
mesh-based network.
A HYBRID PUSH-PULL OVERLAY NETWORK FOR PEER-TO-PEER VIDEO STREAMINGijp2p
In this paper, we have proposed a hybrid push-pull protocol for peer-to-peer live video streaming. The
main goal of this research is to minimize the network end-to-end delay in comparison to pure mesh
networks. Hybrid protocols, in most cases, suffer from complex construction and maintenance. Therefore,
our proposed protocol uses a pure mesh topology and a single layer video coding. In summary, our pushpull protocol has two parts. The pull-based part which is done on the mesh network, and the push-based
part which consists of two phases: parent selection and tree construction. When a push procedure appears,
it is very important to prevent data redundancy. To satisfy this condition, we have introduced a parent
selection method. In this method, by parent selection based on the minimum arrival time, the most stable
node will be selected. This node has the advantage of maximizing the expected service time of the tree.
Using this method, there is no need for maintaining any extra information and topology control data.
Finally, we do performance evaluation using OMNeT++ simulator. The simulation results show that the
proposed architecture has better performance in start-up delay, end-to-end delay, and distortion than pure
mesh-based network.
This document analyzes the minimum delay bounds of chunk-based peer-to-peer video streaming systems. It finds that the uploading bandwidth of peers cannot be utilized to upload video chunks until the download of that chunk is complete, setting a limit on how fast chunks can disseminate. The document derives delay bounds for homogeneous and heterogeneous networks, and proposes a "snowball streaming" algorithm that approaches the minimum delay bound by prioritizing chunk dissemination to peers with the most bandwidth. Simulations show this algorithm achieves closer-to-optimal delays than static multi-tree streaming solutions.
In this paper, we have proposed a hybrid push-pull protocol for peer-to-peer live video streaming. The
main goal of this research is to minimize the network end-to-end delay in comparison to pure mesh
networks. Hybrid protocols, in most cases, suffer from complex construction and maintenance. Therefore,
our proposed protocol uses a pure mesh topology and a single layer video coding. In summary, our pushpull
protocol has two parts. The pull-based part which is done on the mesh network, and the push-based
part which consists of two phases: parent selection and tree construction. When a push procedure appears,
it is very important to prevent data redundancy. To satisfy this condition, we have introduced a parent
selection method. In this method, by parent selection based on the minimum arrival time, the most stable
node will be selected. This node has the advantage of maximizing the expected service time of the tree.
Using this method, there is no need for maintaining any extra information and topology control data.
Finally, we do performance evaluation using OMNeT++ simulator. The simulation results show that the
proposed architecture has better performance in start-up delay, end-to-end delay, and distortion than pure
mesh-based network.
Ontology-Based Routing for Large-Scale Unstructured P2P Publish/Subscribe Systemtheijes
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
The papers for publication in The International Journal of Engineering& Science are selected through rigorous peer reviews to ensure originality, timeliness, relevance, and readability.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This document summarizes and evaluates scheduling algorithms for wireless IP networks that support multiclass traffic. It begins by describing the challenges of providing quality of service (QoS) over wireless networks due to time-varying transmission quality and location-dependent errors. It then reviews existing scheduling algorithms like weighted fair queuing (WFQ) and discusses their limitations in wireless environments. The document proposes a new scheduling mechanism that differentiates service between traffic classes and subclasses, allows compensation for non-real time traffic, and adjusts weights of real-time flows in error states to maintain throughput. Overall, the scheduling algorithm aims to provide QoS, fairness between flows, and flexibility to adapt to changing wireless channel conditions.
Experimental evaluation of scalability and reliability of a feedback based up...ijma
As a result of rapidly changing traffic characteristics in QoS-enabled networks oftentimes renegotiating
the bandwidth requirements are needed. Once renegotiation is started, the sender keeps this process of
invoking renegotiation until new requirements can be fulfilled (or until connection is eventually
terminated.) The frequency of polling the network is delicate balance between huge traffic overhead traffic
with decreased throughput and under-utilization of the network. While driving optimal follow-up rate is a
hard problem, several efficient solutions have been proposed. We have earlier proposed a Scalable
Feedback Based UPC-Parameters Renegotiation Protocol for ATM networks which gives efficient solution
to this problem. The proposed solution minimizes the overhead by shifting the repeated polling away from
the senders/users. Experimental evaluation of scalability and reliability aspects of our solution is presented
in this paper.
Fast Distribution of Replicated Content to Multi- Homed ClientsIDES Editor
Clients can potentially have access to more than
one communication network nowadays due to the availability
of a wide variety of access technologies. On the other hand,
service replication has become a trivial approach in overlay
networks to provide a high availability of data and better QoS.
In this paper, we consider such a multi-homed client seeking
a replicated service in overlay network (e.g., CDN, peer-topeer).
Our aim is to improve the content distribution by
proposing a new model for being applied at the applicationlevel
and in a fully distributed way. Basically, our model
proposes to determine the best mirror server that could be
reached through each client’s network interface based on
application utility function. Then, it consists of downloading
the requested content from the determined best servers
simultaneously through their associated interfaces. Each best
server should deliver a specific estimated range of bytes (i.e.,
content chunk) to an independent TCP socket opened at the
client side for being finally aggregated at the applicationlevel.
Our real experiments show that our model is able to
considerably improve the QoS (e.g., content transfer time)
perceived by the client comparing to the traditional content
distribution techniques.
Peer-to-Peer streaming technology has become one of the major Internet applications as it offers the opportunity of broadcasting high quality video content to a large number of peers with low costs. It is widely accepted that with the efficient utilization of peers and server's upload capacities, peers can enjoy watching a high bit rate video with minimal end-to-end delay. In this paper, we present a practical scheduling algorithm that works in the challenging condition where no spare capacity is available, i.e., it maximally utilizes the resources and broadcasts the maximum streaming rate. Each peer contacts with only a small number of neighbours in the overlay network and autonomously subscribes to sub-streams according to a budget-model in such a way that the number of peers forwarding exactly one sub-stream will be maximized. The hop-count delay is also taken into account to construct a short depth trees. Finally, we show through simulation that peers dynamically converge to an efficient overlay structure with a short hop-count delay. Moreover, the proposed scheme gives nice features in the homogeneous case and overcomes SplitStream in all simulated scenarios.
This document summarizes a study on the performance of LTE networks. The researchers conducted passive and active measurements on a commercial LTE network with over 300,000 users to analyze network characteristics and resource utilization. They found that while LTE provides higher bandwidth than 3G, TCP flows often underutilize available bandwidth due to factors like limited receive windows. On average, flows used only 52% of available bandwidth, lengthening transfers and wasting energy. The researchers developed techniques to estimate bandwidth and identify inefficient application behaviors to recommend protocol and design improvements.
QoS Oriented Coding For Mobility Constraint in Wireless Networksiosrjce
IOSR Journal of Electronics and Communication Engineering(IOSR-JECE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of electronics and communication engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in electronics and communication engineering. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
The document proposes a framework for maximizing the aggregate utility of traffic flows in a wireless mesh network while meeting minimum rate requirements and accounting for interference. It formulates the problem as an optimization that assigns transmission parameters like power, channels, and time slots. If minimum rates cannot be met for all flows, the framework intelligently rejects some flows and recalculates resource allocation. It aims to enhance quality of service support compared to prior work in wired networks by addressing self-interference challenges in wireless multi-hop networks.
Implementing a Session Aware Policy Based Mechanism for QoS Control in LTEIJERA Editor
Quality of Service (QoS) provisioning has become significant with the widely growth of multimedia applications and high increase in the number of users in both wireless and wired networks. In this paper, we implemented a session-aware policy based mechanism for QoS provisioning and control in LTE (Long Term Evolution) networks. Policies are a set of rules identifying the QoS parameters for users. Implementation included DiffServ (Differentiated Services) configuration and setting policies inside the PCRF (Policy Charging Rules Function) which is the brain entity in LTE, then mapping from QCI (QoS Class ID) to DiffServ. Moreover, the dialogue between PCEF (Policy Charging Enforcement Function) and PCRF was implemented. Simulations on four different traffic application types: VoIP (voice over IP), video, web, and ftp (file transfer protocol) were performed under the network simulator (ns2). Results showed that applying PCEF over the different traffic applications has a great effect in controlling these applications and specifically UDP (User Datagram Protocol) based applications such as video.
1 improvement of tcp congestion window over ltetanawan44
This document discusses improving the performance of TCP congestion control over LTE-Advanced networks. It proposes a new congestion avoidance mechanism that uses the available bandwidth of the connection to better detect the network path capacity and improve congestion avoidance. The mechanism is tested using the NS-2 network simulator to model LTE-Advanced traffic. The document provides background on LTE-Advanced network architecture and existing TCP congestion control mechanisms. It aims to develop an enhanced TCP variant that can efficiently transfer high data rates over the large bandwidth, low latency links of LTE-Advanced networks.
Enhanced Protocol for Wireless Content-Centric Network csandit
Recently, Content-Centric Networking (CCN) was intr
oduced and is expected as a new concept
of future internet architecture. Even though CCN is
initially studied for wired networks,
recently, it is also studied for wireless environme
nt. In this paper, we discuss improvement
method for efficient content flooding over wireless
CCNs. The proposed scheme of this paper
use MAC Address of nodes when Interest and Data Pac
ket are forwarded in order to limit the
area of flooding of packets. The proposed protocol
not only reduces the spread of Data packets,
but also offers priority of forwarding to nodes of
shortest path. As a consequence, it reduce
content download time which is proved by extensive
simulations.
Congestion control in packet switched wide area networks using a feedback modelijcses
In a complex world, where networking expands very rapidly, the network stability of flow of bandwidth
played a vital role in transmitting packets. Hence, it was imperative to find solution to the problem of
congestion especially in the follow of bandwidth stability.
Congestion in computer networking is caused by so many factors. Some of the signs are packet loss,
queuing delay resulting from overloading the buffer, faulty hardware devices, intermixing of old and new
technologies and unstable flow of bandwidth resulting from positive feedback
Practical active network services within content-aware gatewaysTal Lavian Ph.D.
The Internet has seen an increase in complexity due to the introduction of new types of networking devices and services, particularly at points of discontinuity known as network edges. As the networking industry continues to add revenue generating services at network edges, there is an increasing need to provide a systematic method for dynamically introducing and providing these new services in lieu of the ad-hoc approach that is in use today. To this end we support a phased approach to "activating" the Internet and suggest that there exists an immediate need for realizing Active Networks concepts at the network edges. In this context, we present our efforts towards the development of a Content-aware Active Gateway (CAG) architecture. With the help of two practical services running on our initial prototype, built from commercial networking devices, we give a qualitative and quantitative view of the CAG potential.
Traffic-aware adaptive server load balancing for softwaredefined networks IJECEIAES
Servers in data center networks handle heterogeneous bulk loads. Load balancing, therefore, plays an important role in optimizing network bandwidth and minimizing response time. A complete knowledge of the current network status is needed to provide a stable load in the network. The process of network status catalog in a traditional network needs additional processing which increases complexity, whereas, in software defined networking, the control plane monitors the overall working of the network continuously. Hence it is decided to propose an efficient load balancing algorithm that adapts SDN. This paper proposes an efficient algorithm TAASLB-traffic-aware adaptive server load balancing to balance the flows to the servers in a data center network. It works based on two parameters, residual bandwidth, and server capacity. It detects the elephant flows and forwards them towards the optimal server where it can be processed quickly. It has been tested with the Mininet simulator and gave considerably better results compared to the existing server load balancing algorithms in the floodlight controller. After experimentation and analysis, it is understood that the method provides comparatively better results than the existing load balancing algorithms.
This document discusses next generation internet over satellite networks. It covers new services and applications for internet integrated services, modeling elastic and inelastic traffic, quality of service provisioning, traffic modeling techniques, and statistical methods for modeling different types of traffic including renewal processes and Markov models. It also discusses traffic engineering principles, multi-protocol label switching, internet protocol version 6, and the future development of satellite networking.
The article looks into the current state of the art of dynamic routing protocols with respect to their
possibilities to react to changes in the Quality of Service when selecting the best route towards a
destination network. New options that could leverage information about the ever changing QoS parameters
for data communication are analysed and a Cisco Performance Routing solution is described more in
detail. The practical part of this work focuses on a design and implementation of a test bed that provides a
scalable laboratory architecture to manipulate QoS parameters of different data communications flowing
through it. The test bed is used in various use cases that were used to evaluate Cisco Performance Routing
optimization capabilities in different scenarios.
Similar to International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015 DOI : 10.5121/ijp2p.2015.6201 1 CONGESTION CONTROL FOR P2P LIVE STREAMING
QOS - LIQUIDSTREAM: SCALABLE MONITORING AND BANDWIDTH CONTROL IN PEER TO PEER...ijp2p
The vast majority of research in P2P live streaming systems focuses on system architectures that offer to
participating peers: high upload bandwidth utilization, low delays during the video stream diffusion,
robustness and stability under dynamic network conditions and peers behavior. On the other hand in order
to guarantee the complete and on time video distribution to every participating peer, the average upload
bandwidth of the participating peers should be always greater than the playback rate of the video stream.
Most of the approaches do not take into consideration this requirement. Thus, in this paper we propose a
very scalable monitoring mechanism of the total upload bandwidth of the participating peers, which is
dynamic, accurate and with low overhead. Moreover, by exploiting this monitoring mechanism we present
and evaluate an algorithm that allows the accurate and on time estimation of the minimal required
additional bandwidth that an external set of resources (e.g. auxiliary peers) have to contribute. In this way
we guarantee the uninterrupted the stream delivery and provide high Quality of Service (QoS) in live
streaming.
A HYBRID PUSH-PULL OVERLAY NETWORK FOR PEER-TO-PEER VIDEO STREAMINGijp2p
In this paper, we have proposed a hybrid push-pull protocol for peer-to-peer live video streaming. The
main goal of this research is to minimize the network end-to-end delay in comparison to pure mesh
networks. Hybrid protocols, in most cases, suffer from complex construction and maintenance. Therefore,
our proposed protocol uses a pure mesh topology and a single layer video coding. In summary, our pushpull protocol has two parts. The pull-based part which is done on the mesh network, and the push-based
part which consists of two phases: parent selection and tree construction. When a push procedure appears,
it is very important to prevent data redundancy. To satisfy this condition, we have introduced a parent
selection method. In this method, by parent selection based on the minimum arrival time, the most stable
node will be selected. This node has the advantage of maximizing the expected service time of the tree.
Using this method, there is no need for maintaining any extra information and topology control data.
Finally, we do performance evaluation using OMNeT++ simulator. The simulation results show that the
proposed architecture has better performance in start-up delay, end-to-end delay, and distortion than pure
mesh-based network.
A HYBRID PUSH-PULL OVERLAY NETWORK FOR PEER-TO-PEER VIDEO STREAMINGijp2p
In this paper, we have proposed a hybrid push-pull protocol for peer-to-peer live video streaming. The
main goal of this research is to minimize the network end-to-end delay in comparison to pure mesh
networks. Hybrid protocols, in most cases, suffer from complex construction and maintenance. Therefore,
our proposed protocol uses a pure mesh topology and a single layer video coding. In summary, our pushpull protocol has two parts. The pull-based part which is done on the mesh network, and the push-based
part which consists of two phases: parent selection and tree construction. When a push procedure appears,
it is very important to prevent data redundancy. To satisfy this condition, we have introduced a parent
selection method. In this method, by parent selection based on the minimum arrival time, the most stable
node will be selected. This node has the advantage of maximizing the expected service time of the tree.
Using this method, there is no need for maintaining any extra information and topology control data.
Finally, we do performance evaluation using OMNeT++ simulator. The simulation results show that the
proposed architecture has better performance in start-up delay, end-to-end delay, and distortion than pure
mesh-based network.
This document analyzes the minimum delay bounds of chunk-based peer-to-peer video streaming systems. It finds that the uploading bandwidth of peers cannot be utilized to upload video chunks until the download of that chunk is complete, setting a limit on how fast chunks can disseminate. The document derives delay bounds for homogeneous and heterogeneous networks, and proposes a "snowball streaming" algorithm that approaches the minimum delay bound by prioritizing chunk dissemination to peers with the most bandwidth. Simulations show this algorithm achieves closer-to-optimal delays than static multi-tree streaming solutions.
In this paper, we have proposed a hybrid push-pull protocol for peer-to-peer live video streaming. The
main goal of this research is to minimize the network end-to-end delay in comparison to pure mesh
networks. Hybrid protocols, in most cases, suffer from complex construction and maintenance. Therefore,
our proposed protocol uses a pure mesh topology and a single layer video coding. In summary, our pushpull
protocol has two parts. The pull-based part which is done on the mesh network, and the push-based
part which consists of two phases: parent selection and tree construction. When a push procedure appears,
it is very important to prevent data redundancy. To satisfy this condition, we have introduced a parent
selection method. In this method, by parent selection based on the minimum arrival time, the most stable
node will be selected. This node has the advantage of maximizing the expected service time of the tree.
Using this method, there is no need for maintaining any extra information and topology control data.
Finally, we do performance evaluation using OMNeT++ simulator. The simulation results show that the
proposed architecture has better performance in start-up delay, end-to-end delay, and distortion than pure
mesh-based network.
Ontology-Based Routing for Large-Scale Unstructured P2P Publish/Subscribe Systemtheijes
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
The papers for publication in The International Journal of Engineering& Science are selected through rigorous peer reviews to ensure originality, timeliness, relevance, and readability.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Enrich multi-channel P2P VoD streaming based on dynamic replication strategyIJAAS Team
Peer-to-Peer Video-on-Demand (VoD) is a favorable solution which compromises thousands of videos to millions of users with completeinteractive video watching stream. Most of the profitable P2P streaming groupsPPLive, PPStream and UUSee have announced a multichannel P2P VoD system that approvals user to view extra one channel at a time. The present multiple channel P2P VoD system resonant a video at a low streaming rate due to the channel resource inequity and channel churn. In order to growth the streaming capacity, this paper highlights completely different effective helpers created resource balancing scheme that actively recognizes the supply-and-demand inequity in multiple channels. Moreover, peers in an extra channel help its unused bandwidth resources to peers in a shortage channel that minimizes the server bandwidth consumption. To provide a desired replication ratio for optimal caching, it develops a dynamic replication strategy that optimally tunes the number of replicas based on dynamic popularity in a distributed and dynamic routine. This work accurately forecasts the varying popularity over time using Auto-Regressive Integrated Moving Average (ARIMA) model, an effective time-series forecasting technique that supports dynamic environment. Experimental assessment displays that the offered dynamic replication strategy which should achieves high streaming capacity under reduced server workload when associated to existing replication algorithms.
PEER-TO-PEER LIVE STREAMING AND VIDEO ON DEMAND DESIGN ISSUES AND ITS CHALLEN...ijp2p
This document discusses the design issues and challenges of peer-to-peer live streaming and video on demand systems. It describes tree-based and mesh-based approaches for live streaming and how they have been adapted for video on demand. Key challenges discussed include maintaining streaming topology as peers join and leave, supporting asynchronous playback, and ensuring sequential block delivery for continuous playback.
Design and evaluation of a proxy cache foringenioustech
The document describes the design and evaluation of pCache, a proxy cache for peer-to-peer (P2P) traffic. Key contributions include:
1) A new storage system optimized for P2P caching that efficiently handles requests for object segments of arbitrary lengths.
2) An algorithm to infer information required for caching P2P traffic when this information is not directly available.
3) Achieving full transparency in the proxy cache and efficiently handling non-P2P connections to reduce processing overhead.
Extensive experiments evaluate pCache using real P2P traffic and show that it benefits both clients and ISPs without hurting P2P network performance.
AN INITIAL PEER CONFIGURATION ALGORITHM FOR MULTI-STREAMING PEER-TO-PEER NETW...ijp2p
The growth of the Internet technology enables us to use network applications for streaming audio and
video.Especially, real-time streaming services using peer-to-peer (P2P) technology are currently
emerging.An important issue on P2P streaming is how to construct a logical network (overlay network) on
a physical network (IP network). In this paper, we propose an initial peer configuration algorithm for a
multi-streaming peer-to-peer network. The proposed algorithm is based on a mesh-pull approach where
any node has multiple parent and child nodes as neighboring nodes, and content transmitted between these
neighboring nodes depends on their parent-child relationships. Our simulation experiments show that the
proposed algorithm improves the number of joining node and traffic load.
AN INITIAL PEER CONFIGURATION ALGORITHM FOR MULTI-STREAMING PEER-TO-PEER NETW...ijp2p
The growth of the Internet technology enables us to use network applications for streaming audio and
video.Especially, real-time streaming services using peer-to-peer (P2P) technology are currently
emerging.An important issue on P2P streaming is how to construct a logical network (overlay network) on
a physical network (IP network). In this paper, we propose an initial peer configuration algorithm for a
multi-streaming peer-to-peer network. The proposed algorithm is based on a mesh-pull approach where
any node has multiple parent and child nodes as neighboring nodes, and content transmitted between these
neighboring nodes depends on their parent-child relationships. Our simulation experiments show that the
proposed algorithm improves the number of joining node and traffic load.
Talhunt is a leader in assisting and executing IEEE Engineering projects to Engineering students - run by young and dynamic IT entrepreneurs. Our primary motto is to help Engineering graduates in IT and Computer science department to implement their final year project with first-class technical and academic assistance.
Project assistance is provided by 15+ years experienced IT Professionals. Over 100+ IEEE 2015 and 200+ yester year IEEE project titles are available with us. Projects are based on Software Development Life-Cycle (SDLC) model.
This document discusses the interaction between application layer multicast (ALM) trees and MPEG-4 video streaming. It examines how different coding parameters and tree structures affect end-user video quality as measured by PSNR. The paper presents a simulation system to test various combinations of NICE ALM trees and MPEG-4 parameters. Results show that coding choices and tree organization depend on network characteristics like packet loss and bandwidth distribution. Large GOP sizes and many B-frames optimize quality with rare losses, while small GOPs and fewer B-frames work best with frequent losses. Uniform bandwidth favors small clusters and long paths, while varied bandwidth prefers larger clusters and shorter paths.
Mobile Hosts Participating in Peer-to-Peer Data Networks: Challenges and Solu...Zhenyun Zhuang
Wireless Networks (2010)
http://dl.acm.org/citation.cfm?id=1873504
Peer-to-peer (P2P) data networks dominate
Internet traffic, accounting for over 60% of the overall
traffic in a recent study. In this work, we study the
problems that arise when mobile hosts participate in
P2P networks. We primarily focus on the performance
issues as experienced by the mobile host, but also study
the impact on other fixed peers. Using BitTorrent as a
key example, we identify several unique problems that
arise due to the design aspects of P2P networks being
incompatible with typical characteristics of wireless
and mobile environments. Using the insights gained
through our study, we present a wireless P2P (wP2P)
client application that is backward compatible with existing
fixed-peer client applications, but when used on
mobile hosts can provide significant performance improvements.
3 S W 2009 I E E E Abstracts Java, N C C T Chennaincct
final Year Projects, Final Year Projects in Chennai, Software Projects, Embedded Projects, Microcontrollers Projects, DSP Projects, VLSI Projects, Matlab Projects, Java Projects, .NET Projects, IEEE Projects, IEEE 2009 Projects, IEEE 2009 Projects, Software, IEEE 2009 Projects, Embedded, Software IEEE 2009 Projects, Embedded IEEE 2009 Projects, Final Year Project Titles, Final Year Project Reports, Final Year Project Review, Robotics Projects, Mechanical Projects, Electrical Projects, Power Electronics Projects, Power System Projects, Model Projects, Java Projects, J2EE Projects, Engineering Projects, Student Projects, Engineering College Projects, MCA Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, Wireless Networks Projects, Network Security Projects, Networking Projects, final year projects, ieee projects, student projects, college projects, ieee projects in chennai, java projects, software ieee projects, embedded ieee projects, "ieee2009projects", "final year projects", "ieee projects", "Engineering Projects", "Final Year Projects in Chennai", "Final year Projects at Chennai", Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, Final Year Java Projects, Final Year ASP.NET Projects, Final Year VB.NET Projects, Final Year C# Projects, Final Year Visual C++ Projects, Final Year Matlab Projects, Final Year NS2 Projects, Final Year C Projects, Final Year Microcontroller Projects, Final Year ATMEL Projects, Final Year PIC Projects, Final Year ARM Projects, Final Year DSP Projects, Final Year VLSI Projects, Final Year FPGA Projects, Final Year CPLD Projects, Final Year Power Electronics Projects, Final Year Electrical Projects, Final Year Robotics Projects, Final Year Solor Projects, Final Year MEMS Projects, Final Year J2EE Projects, Final Year J2ME Projects, Final Year AJAX Projects, Final Year Structs Projects, Final Year EJB Projects, Final Year Real Time Projects, Final Year Live Projects, Final Year Student Projects, Final Year Engineering Projects, Final Year MCA Projects, Final Year MBA Projects, Final Year College Projects, Final Year BE Projects, Final Year BTech Projects, Final Year ME Projects, Final Year MTech Projects, Final Year M.Sc Projects, IEEE Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, IEEE 2009 Java Projects, IEEE 2009 ASP.NET Projects, IEEE 2009 VB.NET Projects, IEEE 2009 C# Projects, IEEE 2009 Visual C++ Projects, IEEE 2009 Matlab Projects, IEEE 2009 NS2 Projects, IEEE 2009 C Projects, IEEE 2009 Microcontroller Projects, IEEE 2009 ATMEL Projects, IEEE 2009 PIC Projects, IEEE 2009 ARM Projects, IEEE 2009 DSP Projects, IEEE 2009 VLSI Projects, IEEE 2009 FPGA Projects, IEEE 2009 CPLD Projects, IEEE 2009 Power Electronics Projects, IEEE 2009 Electrical Projects, IEEE 2009 Robotics Projects, IEEE 2009 Solor Projects, IEEE 2009 MEMS Projects, IEEE 2009 J2EE P
final Year Projects, Final Year Projects in Chennai, Software Projects, Embedded Projects, Microcontrollers Projects, DSP Projects, VLSI Projects, Matlab Projects, Java Projects, .NET Projects, IEEE Projects, IEEE 2009 Projects, IEEE 2009 Projects, Software, IEEE 2009 Projects, Embedded, Software IEEE 2009 Projects, Embedded IEEE 2009 Projects, Final Year Project Titles, Final Year Project Reports, Final Year Project Review, Robotics Projects, Mechanical Projects, Electrical Projects, Power Electronics Projects, Power System Projects, Model Projects, Java Projects, J2EE Projects, Engineering Projects, Student Projects, Engineering College Projects, MCA Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, Wireless Networks Projects, Network Security Projects, Networking Projects, final year projects, ieee projects, student projects, college projects, ieee projects in chennai, java projects, software ieee projects, embedded ieee projects, "ieee2009projects", "final year projects", "ieee projects", "Engineering Projects", "Final Year Projects in Chennai", "Final year Projects at Chennai", Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, Final Year Java Projects, Final Year ASP.NET Projects, Final Year VB.NET Projects, Final Year C# Projects, Final Year Visual C++ Projects, Final Year Matlab Projects, Final Year NS2 Projects, Final Year C Projects, Final Year Microcontroller Projects, Final Year ATMEL Projects, Final Year PIC Projects, Final Year ARM Projects, Final Year DSP Projects, Final Year VLSI Projects, Final Year FPGA Projects, Final Year CPLD Projects, Final Year Power Electronics Projects, Final Year Electrical Projects, Final Year Robotics Projects, Final Year Solor Projects, Final Year MEMS Projects, Final Year J2EE Projects, Final Year J2ME Projects, Final Year AJAX Projects, Final Year Structs Projects, Final Year EJB Projects, Final Year Real Time Projects, Final Year Live Projects, Final Year Student Projects, Final Year Engineering Projects, Final Year MCA Projects, Final Year MBA Projects, Final Year College Projects, Final Year BE Projects, Final Year BTech Projects, Final Year ME Projects, Final Year MTech Projects, Final Year M.Sc Projects, IEEE Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, IEEE 2009 Java Projects, IEEE 2009 ASP.NET Projects, IEEE 2009 VB.NET Projects, IEEE 2009 C# Projects, IEEE 2009 Visual C++ Projects, IEEE 2009 Matlab Projects, IEEE 2009 NS2 Projects, IEEE 2009 C Projects, IEEE 2009 Microcontroller Projects, IEEE 2009 ATMEL Projects, IEEE 2009 PIC Projects, IEEE 2009 ARM Projects, IEEE 2009 DSP Projects, IEEE 2009 VLSI Projects, IEEE 2009 FPGA Projects, IEEE 2009 CPLD Projects, IEEE 2009 Power Electronics Projects, IEEE 2009 Electrical Projects, IEEE 2009 Robotics Projects, IEEE 2009 Solor Projects, IEEE 2009 MEMS Projects, IEEE 2009 J2EE P
This document provides summaries of IEEE papers from various years between 2007-2009. It instructs the user to use Ctrl + F to search for papers from a specific year. For example, searching for "2009" would yield over 50 project summaries from that year. The document then provides an excerpt from an IEEE paper from 2009 on location-based services and privacy.
This document provides summaries of IEEE papers from various years between 2007-2009. It instructs the user to use Ctrl + F to search for papers from a specific year. For example, searching for "2009" would yield over 50 project summaries from that year. The document then provides an excerpt from an IEEE paper from 2009 on location-based services and privacy.
Real Time Projects, Live Projects, Student Projects, Engineering Projectsncct
final Year Projects, Final Year Projects in Chennai, Software Projects, Embedded Projects, Microcontrollers Projects, DSP Projects, VLSI Projects, Matlab Projects, Java Projects, .NET Projects, IEEE Projects, IEEE 2009 Projects, IEEE 2009 Projects, Software, IEEE 2009 Projects, Embedded, Software IEEE 2009 Projects, Embedded IEEE 2009 Projects, Final Year Project Titles, Final Year Project Reports, Final Year Project Review, Robotics Projects, Mechanical Projects, Electrical Projects, Power Electronics Projects, Power System Projects, Model Projects, Java Projects, J2EE Projects, Engineering Projects, Student Projects, Engineering College Projects, MCA Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, Wireless Networks Projects, Network Security Projects, Networking Projects, final year projects, ieee projects, student projects, college projects, ieee projects in chennai, java projects, software ieee projects, embedded ieee projects, "ieee2009projects", "final year projects", "ieee projects", "Engineering Projects", "Final Year Projects in Chennai", "Final year Projects at Chennai", Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, Final Year Java Projects, Final Year ASP.NET Projects, Final Year VB.NET Projects, Final Year C# Projects, Final Year Visual C++ Projects, Final Year Matlab Projects, Final Year NS2 Projects, Final Year C Projects, Final Year Microcontroller Projects, Final Year ATMEL Projects, Final Year PIC Projects, Final Year ARM Projects, Final Year DSP Projects, Final Year VLSI Projects, Final Year FPGA Projects, Final Year CPLD Projects, Final Year Power Electronics Projects, Final Year Electrical Projects, Final Year Robotics Projects, Final Year Solor Projects, Final Year MEMS Projects, Final Year J2EE Projects, Final Year J2ME Projects, Final Year AJAX Projects, Final Year Structs Projects, Final Year EJB Projects, Final Year Real Time Projects, Final Year Live Projects, Final Year Student Projects, Final Year Engineering Projects, Final Year MCA Projects, Final Year MBA Projects, Final Year College Projects, Final Year BE Projects, Final Year BTech Projects, Final Year ME Projects, Final Year MTech Projects, Final Year M.Sc Projects, IEEE Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, IEEE 2009 Java Projects, IEEE 2009 ASP.NET Projects, IEEE 2009 VB.NET Projects, IEEE 2009 C# Projects, IEEE 2009 Visual C++ Projects, IEEE 2009 Matlab Projects, IEEE 2009 NS2 Projects, IEEE 2009 C Projects, IEEE 2009 Microcontroller Projects, IEEE 2009 ATMEL Projects, IEEE 2009 PIC Projects, IEEE 2009 ARM Projects, IEEE 2009 DSP Projects, IEEE 2009 VLSI Projects, IEEE 2009 FPGA Projects, IEEE 2009 CPLD Projects, IEEE 2009 Power Electronics Projects, IEEE 2009 Electrical Projects, IEEE 2009 Robotics Projects, IEEE 2009 Solor Projects, IEEE 2009 MEMS Projects, IEEE 2009 J2EE P
Similar to International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015 DOI : 10.5121/ijp2p.2015.6201 1 CONGESTION CONTROL FOR P2P LIVE STREAMING (20)
COMPARATIVE STUDY OF CAN, PASTRY, KADEMLIA AND CHORD DHTSijp2p
Peer-to-Peer (P2P) systems allow decentralization, sharing of all the resources of a network with direct
communication and collaboration between nodes. There are three main families of P2P networks: the
centralized architecture, the decentralized architecture that can be structured or unstructured and the
hybrid architecture. Today, there are several implementations for structured decentralized architectures.
This implies that the insertion and search algorithms are different. Among them we have; Chord, Pastry,
Kademlia, CAN(Content Addressable Network) . The choice of these DHTs (Distributed Hash Table) for an
application is made on the basis of their performances. Studies of each of these DHTs mentioned have been
done, proving their performance. But a comparative study of the four DHTs Chord, Pastry, CAN, Kademlia
has not been clearly addressed by previous works. In this paper, we have conducted a comparative
theoretical study of the DHTs Chord, Pastry, CAN, Kademlia. Then, by simulation, we have evaluated the
performances in terms of latency, number of hops and number of transmitted messages. Our study clearly
shows the differences between mathematically established performance and actual performance in an
environment with less restriction. This analysis was made from the data obtained by using the simple
network layer of the PeerfactSim simulator. This simulator abstracts the different network layers, which
gives the advantage of testing the performances with reasonable accuracy. The use of the single network
layer can be considered an ideal case because the node searches are done locally.
International Journal of Peer to Peer Networks .docxijp2p
The International Journal of peer-to-peer networking is a quarterly open access peer-reviewed journal that publishes articles that contribute new results in all areas of P2P Networks. The journal provides a platform to disseminate new ideas and new research, advance theories, and propagate best practices in the area of P2P networking. This will include works that relate to peer-to-peer systems, peer-to-peer applications, grid systems, large-scale distributed systems, and overlay networks. The journal offers a forum in which academics, consultants, and practitioners in a variety of fields can exchange ideas to further research and improve practices in all areas of P2P.
Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of P2P networks.
International Journal of peer-to-peer networks (IJP2P)ijp2p
The International Journal of peer-to-peer networking is a quarterly open access peer-reviewed journal that publishes articles that contribute new results in all areas of P2P Networks. The journal provides a platform to disseminate new ideas and new research, advance theories, and propagate best practices in the area of P2P networking.
International Journal of peer-to-peer networks (IJP2P)ijp2p
The International Journal of peer-to-peer networking is a quarterly open access peer-reviewed journal that publishes articles that contribute new results
in all areas of P2P Networks. The journal provides a platform to disseminate new ideas and new research, advance theories, and propagate best
practices in the area of P2P networking. This will include works that relate to peer-to-peer systems, peer-to-peer applications, grid systems,
large-scale distributed systems, and overlay networks. The journal offers a forum in which academics, consultants, and practitioners in a variety
of fields can exchange ideas to further research and improve practices in all areas of P2P.
2nd International Conference on Big Data, IoT and Machine Learning (BIOM 2022)ijp2p
2nd International Conference on Big Data, IoT and Machine Learning (BIOM 2022) will act as a major forum for the presentation of innovative ideas, approaches, developments, and research projects in the areas of Big Data, Internet of Things (IoT) and Machine Learning. It will also serve to facilitate the exchange of information between researchers and industry professionals to discuss the latest issues and advancement in the area of Big Data, IoT and Machine Learning.
7th International Conference on Networks, Communications, Wireless and Mobile...ijp2p
7th International Conference on Networks, Communications, Wireless and Mobile Computing (NCWMC 2022) looks for significant contributions to the Computer Networks, Communications, wireless and mobile computing for wired and wireless networks in theoretical and practical aspects. Original papers are invited on computer Networks, network protocols and wireless networks, Data communication Technologies, network security and mobile computing. The goal of this Conference is to bring together researchers and practitioners from academia and industry to focus on advanced networking concepts and establishing new collaborations in these areas.
4th International Conference on Internet of Things (CIoT 2022)ijp2p
4th International Conference on Internet of Things (CIoT 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of IoT.
11th International conference on Parallel, Distributed Computing and Applicat...ijp2p
11th International conference on Parallel, Distributed Computing and Applications (IPDCA 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Parallel, Distributed Computing. Original papers are invited on Algorithms and Applications, computer Networks, Cyber trust and security, Wireless networks and mobile Computing and Bioinformatics. The aim of the conference is to provide a platform to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development in the field.
3rd International Conference on Machine learning and Cloud Computing (MLCL 2022)ijp2p
3rd International Conference on Machine learning and Cloud Computing (MLCL 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Cloud computing. The aim of the conference is to provide a platform to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development in the field.
4th International Conference on Internet of Things (CIoT 2022) ijp2p
4th International Conference on Internet of Things (CIoT 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of IoT.
4th International Conference on Internet of Things (CIoT 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of IoT.
International Journal of peer-to-peer networks (IJP2P)ijp2p
The International Journal of peer-to-peer networking is a quarterly open access peer-reviewed journal that publishes articles that contribute new results in all areas of P2P Networks. The journal provides a platform to disseminate new ideas and new research, advance theories, and propagate best practices in the area of P2P networking. This will include works that relate to peer-to-peer systems, peer-to-peer applications, grid systems, large-scale distributed systems, and overlay networks. The journal offers a forum in which academics, consultants, and practitioners in a variety of fields can exchange ideas to further research and improve practices in all areas of P2P.
3rd International Conference on Networks, Blockchain and Internet of Things (...ijp2p
3rd International Conference on Networks, Blockchain and Internet of Things (NBIoT 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Networks, Blockchain and Internet of Things. The Conference looks for significant contributions to all major fields of the Networks, Blockchain and Internet of Things in theoretical and practical aspects.
Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the following areas but are not limited to:
3rd International Conference on NLP & Information Retrieval (NLPI 2022)ijp2p
3rd International Conference on NLP & Information Retrieval (NLPI 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Natural Language Computing and Information Retrieval.
Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the following areas, but are not limited to.
CALL FOR PAPERS - 14th International Conference on Wireless & Mobile Networks...ijp2p
14th International Conference on Wireless & Mobile Networks (WiMoNe 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Wireless & Mobile computing Environment. Current information age is witnessing a dramatic use of digital and electronic devices in the workplace and beyond. Wireless, Mobile Networks & its applications had received a significant and sustained research interest in terms of designing and deploying large scale and high performance computational applications in real life. The aim of the conference is to provide a platform to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development in the field.
PUBLISH YOUR PAPER - INTERNATIONAL JOURNAL OF PEER-TO-PEER NETWORKS (IJP2P)ijp2p
Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of P2P networks.
International Journal of peer-to-peer networks (IJP2P)ijp2p
The International Journal of peer-to-peer networking is a quarterly open access peer-reviewed journal that publishes articles that contribute new results in all areas of P2P Networks. The journal provides a platform to disseminate new ideas and new research, advance theories, and propagate best practices in the area of P2P networking. This will include works that relate to peer-to-peer systems, peer-to-peer applications, grid systems, large-scale distributed systems, and overlay networks. The journal offers a forum in which academics, consultants, and practitioners in a variety of fields can exchange ideas to further research and improve practices in all areas of P2P.
3rd International Conference on Blockchain and Internet of Things (BIoT 2022)ijp2p
3rd International Conference on Blockchain and Internet of Things (BIoT 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and
applications of Blockchain and Internet of Things. The Conference looks for significant contributions to all major fields of the Blockchain and Internet of Things in theoretical and
practical aspects. Authors are solicited to contribute to the conference by submitting articles that illustrate research
results, projects, surveying works and industrial experiences that describe significant advances in the areas of Blockchain and Internet of Things.
International Journal of peer-to-peer networks (IJP2P)ijp2p
The International Journal of peer-to-peer networking is a quarterly open access peer-reviewed journal that publishes articles that contribute new results in all areas of P2P Networks. The journal provides a platform to disseminate new ideas and new research, advance theories, and propagate best practices in the area of P2P networking. This will include works that relate to peer-to-peer systems, peer-to-peer applications, grid systems, large-scale distributed systems, and overlay networks. The journal offers a forum in which academics, consultants, and practitioners in a variety of fields can exchange ideas to further research and improve practices in all areas of P2P.
CALL FOR PAPERS - 4th International Conference on Internet of Things (CIoT 2022)ijp2p
4th International Conference on Internet of Things (CIoT 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of IoT.
Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of Internet of Things.
Gen Z and the marketplaces - let's translate their needsLaura Szabó
The product workshop focused on exploring the requirements of Generation Z in relation to marketplace dynamics. We delved into their specific needs, examined the specifics in their shopping preferences, and analyzed their preferred methods for accessing information and making purchases within a marketplace. Through the study of real-life cases , we tried to gain valuable insights into enhancing the marketplace experience for Generation Z.
The workshop was held on the DMA Conference in Vienna June 2024.
Discover the benefits of outsourcing SEO to Indiadavidjhones387
"Discover the benefits of outsourcing SEO to India! From cost-effective services and expert professionals to round-the-clock work advantages, learn how your business can achieve digital success with Indian SEO solutions.
HijackLoader Evolution: Interactive Process HollowingDonato Onofri
CrowdStrike researchers have identified a HijackLoader (aka IDAT Loader) sample that employs sophisticated evasion techniques to enhance the complexity of the threat. HijackLoader, an increasingly popular tool among adversaries for deploying additional payloads and tooling, continues to evolve as its developers experiment and enhance its capabilities.
In their analysis of a recent HijackLoader sample, CrowdStrike researchers discovered new techniques designed to increase the defense evasion capabilities of the loader. The malware developer used a standard process hollowing technique coupled with an additional trigger that was activated by the parent process writing to a pipe. This new approach, called "Interactive Process Hollowing", has the potential to make defense evasion stealthier.
Ready to Unlock the Power of Blockchain!Toptal Tech
Imagine a world where data flows freely, yet remains secure. A world where trust is built into the fabric of every transaction. This is the promise of blockchain, a revolutionary technology poised to reshape our digital landscape.
Toptal Tech is at the forefront of this innovation, connecting you with the brightest minds in blockchain development. Together, we can unlock the potential of this transformative technology, building a future of transparency, security, and endless possibilities.
International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015 DOI : 10.5121/ijp2p.2015.6201 1 CONGESTION CONTROL FOR P2P LIVE STREAMING
1. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
DOI : 10.5121/ijp2p.2015.6201 1
CONGESTION CONTROL FOR P2P LIVE STREAMING
Nikolaos Efthymiopoulos1
, Athanasios Christakidis1
, Maria Efthymiopoulou1
,
Loris Corazza1
, Spyros Denazis1
1
Department of Electrical and Computer Engineering, University of Patras, Patras,
Greece
ABSTRACT
In recent years, research efforts tried to exploit peer-to-peer (P2P) systems in order to provide Live
Streaming (LS) and Video-on-Demand (VoD) services. Most of these research efforts focus on the
development of distributed P2P block schedulers for content exchange among the participating peers and
on the characteristics of the overlay graph (P2P overlay) that interconnects the set of these peers.
Currently, researchers try to combine peer-to-peer systems with cloud infrastructures. They developed
monitoring and control architectures that use resources from the cloud in order to enhance QoS and
achieve an attractive trade-off between stability and low cost operation. However, there is a lack of
research effort on the congestion control of these systems and the existing congestion control architectures
are not suitable for P2P live streaming traffic (small sequential non persistent traffic towards multiple
network locations). This paper proposes a P2P live streaming traffic aware congestion control protocol
that: i) is capable to manage sequential traffic heading to multiple network destinations , ii) efficiently
exploits the available bandwidth, iii) accurately measures the idle peer resources, iv) avoids network
congestion, and v) is friendly to traditional TCP generated traffic. The proposed P2P congestion control
has been implemented, tested and evaluated through a series of real experiments powered across the
BonFIRE infrastructure.
KEYWORDS
Peer to Peer, Live Streaming, Congestion Control
1. INTRODUCTION
Video streaming has become a dominant part of today's internet traffic. As analysed in [7]
between 2012 and 2013, the highest growth happened on the Internet side in online video with 16
per cent year-over-year growth. By 2018, digital TV and online video will be the two most highly
penetrated services, with 86 per cent and 78 per cent respectively. Additionally is considered that
the market is growing with very good chances of very high penetration of these services to new
internet users. On the other hand the tremendous number of users with heterogeneous capabilities
leads even the major streaming service providers (e.g. YouTube) to suffer from high bandwidth
costs. Peer-to-peer live streaming and video on demand architectures [2],[6],[25] have received a
lot of research attention in the past few years aiming at achieving a better trade-off between
bandwidth costs and quality of the transmitted video, while providing scalability and stability of
these services. In more detail, the major requirements for P2P live streaming systems are:
Efficiency of the video distribution, as analysed in [1],[2],[3],[14], in terms of upload bandwidth
utilization of participating peers. The goal here is to minimize the additional bandwidth that is
contributed by a set of media servers (cloud). Efficiency has a direct impact on the trade-off
between bandwidth costs and video quality.
2. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
2
Stability of the system, as described in [4],[5],[20],[21],[22],[23],[24], in the presence of dynamic
conditions. The stability of the system is greatly affected by the dynamic conditions of the
underlying network. The total P2P overlay bandwidth also changes quite frequently due to peer
arrival and departures. These conditions have a serious impact in the quality of service (QoS) and
consequently in the quality of experience (QoE). A stable P2P live steaming system must be able
to monitor and react to these changes.
Scalability property of such systems is determined by the amount of bandwidth and processing
overhead that media servers have to contribute as the number of participating peers grows. For
the design of a scalable system, this overhead has to remain low even in cases that the number of
participating peers is large.
A P2P overlay is a graph in which each node represents a user, and each edge that connects two
nodes represents the exchange of video blocks between users. Several methods [2],[14],[3] have
been proposed that try to optimize this graph in order to achieve stability and maximum
exploitation of the available bandwidth of the participating peers while simultaneously they
exploit network locality [2],[27]. These works assume the a priori knowledge of the dynamic
upload bandwidth even in cases where peers fail to fully exploiting it. Under this observation
there is a need for a P2P congestion control architecture which will be able to provide this
information to P2P overlay optimization architectures in order to make their implementation in
real P2P streaming systems feasible.
Currently, monitoring and control systems have been proposed [5],[8],[1],[29] that try, in a
scalable and dynamic fashion, to monitor the available resources of a P2P overlay in order to
calculate the deficit or surplus of its aggregate upload bandwidth. In this way, in case of deficit,
they allocate dynamically additional upload bandwidth or, in case of surplus, they exploit it for
other purposes. Nevertheless, these attempts, and other that explore the dynamics of P2P live
streaming [26],[28] are based on the dynamic and accurate estimation of the idle upload
bandwidth of each participating peer and its upload bandwidth capacity that a successful P2P
congestion control architecture will offer.
Although there is a vast amount of literature, which analysed in detail in [9], on congestion
control for point-to-point bulk data transfers, there are only very few works regarding P2P
congestion control. An approach that concerns P2P traffic is LEBDAT [13] but it is suitable for a
P2P file sharing system where: i) traffic is persistent, ii) traffic consisted from much larger blocks
than those used in P2P LS and VoD , iii)there are no delay constraints in the application. Only a
recent approach that described in [12] proposes a congestion control algorithm for P2P live
streaming. Despite its good features it assumes persistent traffic and transmits in parallel the
various video blocks to multiple receivers. In this way resources are wasted in case of no
persistent traffic and the latency for the reception of a block is highly increased. Thus it doesn’t
achieve low delay which is an essential requirement in P2P live streaming systems.
Motivated by the lack of critical mass of research in the area of congestion control for P2P LS
and VoD systems and the serious issues raised above, we have designed, implemented and
evaluated in a real environment a congestion control P2P architecture that:
• Is suitable for highly dynamic traffic characterized by sequential transmissions to
different network locations (P2P video blocks)
• It efficiently utilizes the upload bandwidth of participating peers
• It remains stable and robust in the eventuality of changes in peer’s upload bandwidth,
time-varying delays and dynamic underlying network conditions
3. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
3
• It accurately and dynamically measures the available upload bandwidth capacity of each
peer and avoids buffer overloading of the participating network devices in the underlying
network (BufferBloat problem)
The reminder of this paper is structured as follows: Section 2 presents our P2P live streaming
system’s architecture. Section 3 provides the problem setting. In Section 4 is analysed the
proposed P2P congestion control architecture. Section 5 presents the P2P congestion control
strategy. Section 6 describes our evaluation test-bed and evaluates the proposed P2P congestion
control architecture. Finally in Section 7 we conclude and highlight our future steps.
2. SYSTEM ARCHITECTURE
Our P2P live video streaming system (Fig. 1) consists of a media server in a cloud, (noted by S)
and a set of peers (noted by N). The cloud is responsible for: i) the initial diffusion of the video to
a small subset of nodes among participating peers, ii) the tracking of the network addresses of
participating peers in order to assist the construction and management of the P2P overlay, iii) the
dynamic and scalable monitor of the resources of participating peers, iv) the dynamic allocation
and release of auxiliary bandwidth.
The video stream that the system disseminates is divided into video blocks. In order to allow
peers to exchange video blocks, each peer maintains network connections with a small subset of
other peers which will be noted as neighbours. The sets of these connections change dynamically
and form a dynamic graph called the P2P overlay. In our previous works [1],[2],[3] we present a
graph topology and P2P overlay management (dynamic and distributed optimization) algorithms
that each peer periodically executes which result in the dynamic reconfiguration of the P2P
overlay. We use distributed optimization theory in order to dynamically ensure in a distributed
(scalable) and dynamic fashion that: i) peers have connections proportional with their upload
bandwidth, ii) peers have connections with other peers close to the underlying network, iii) our
P2P overlay is adaptable to underlying network changes and peer arrivals and departures. This
allows us to efficiently exploit all the available bandwidth resources even if they are highly
heterogeneous.
The dynamic output of the P2P overlay management algorithms that run in each participating
peer is a neighbour list that is passed in the Distributed Block Transmission Scheduler.
Figure 1. Proposed P2P live streaming system architecture
After that, video block exchanges are coordinated by the Distributed Media-Block Transmission
Scheduler (DBTS) which is comprised by a set of algorithms executed by every peer who
4. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
4
dynamically communicates with its neighbours. The major objective of DBTS is to ensure the
timely delivery of every video block to every peer by exploiting the upload bandwidth of
participating peers and the additional bandwidth resources that media servers (cloud) may
contribute. Each peer periodically sends to its neighbours control messages which encapsulate
information about video blocks that it owns. Thus, periodically each peer (through a matching
algorithm) is able to request from each one of its neighbours a different video block or nothing if
there is no video block to request. In order to perform the requests a matching algorithm is
executed periodically by each peer and its objective is to request as many unique blocks as
possible. These requests are served sequentially by each peer who prioritizes them by selecting
each time its most deprived neighbour to serve its block request. As most deprived is defined the
neighbour that has the smallest total number of blocks compared to the video blocks that sender
peer owns. Our proposed DBTS is analysed in detail in our previous works [1],[2],[3]. DBTS
sends the video blocks that have to be sent in the P2P congestion control component and the
ordered stream with the blocks that it receives to the video player.
Our proposed P2P overlay and our DBTS enhance our P2P live streaming system with two
properties. The first property (Property 1) is that if idle bandwidth exists it is derived from
bandwidth surplus in the system and not from the inefficiency of the system to exploit it. In other
words, we guarantee that the presence of idle bandwidth implies (testifies) the complete stream
delivery. The second property is that the percentages of the idle resources among participating
peers are almost equal (Property 2). We highlight here that in case of heterogeneous peer upload
bandwidth various peers send with various bitrates (analog with their upload bandwidth capacity)
but the percentage of their bandwidth utilization, and so the percentage of their idle time is very
similar.
By exploiting the aforementioned properties we developed two components responsible for the
monitoring of the total upload bandwidth of the P2P overlay and the control of the auxiliary
upload bandwidth and the playback rate in order to have a stable P2P live streaming system.
These are background work and we describe them in detail in [18] and [19].
We note the first as Scalable Bandwidth Monitoring (SBM) in which a scalable gossip protocol
that is connected with a centralized component in the cloud and : i) aggregates the monitoring
information from DBTS and P2P congestion control, ii) forms all the required metrics that QoS
enabler needs.
QoS Enabler, which is the second one, has to calculate dynamically the amount of total system's
upload bandwidth surplus or deficit towards the control of the idle bandwidth resources. In order
to achieve this it: i) add or remove dynamically the amount of upload bandwidth that is needed as
this is determined by the bandwidth allocation control strategy and/or ii) adapt the playback rate
to the available resources.
Our P2P congestion control is able to manage sequential transmissions of video blocks to
multiple locations that DBTS sends to it and to provide to the Scalable Bandwidth Monitoring
and to the P2P overlay the dynamic estimation of: i) the upload bandwidth capacity, ii) the idle
bandwidth resources of each participating peer with the way that will be requested from the latter.
In the rest of this work we describe this component in detail.
3. PROBLEM STATEMENT
Without loss of generality, we assume that the source of congestion problems lies with the
uploading capabilities of the peers rather than the downloading. Likewise, the problem will be
5. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
5
aggravated by the incoming edge of the network (usually home gateways or DSLAM) as they
may act as the primary bottleneck for any of the outgoing flows including P2P flows.
Accordingly, the goal of the congestion control method is to control the queue size of this
bottleneck node by controlling the number of network packets that should be injected to the
network. From the viewpoint of the P2P LS or VoD, this queue should always be non-empty, in
order to fully utilize the available bandwidth provided of course that the application has the
necessary blocks to transmit. In addition, its size shouldn’t increase over time as this would lead
to congestion problems and packet loss. The control of this queue is carried out by observing the
latencies between the source sender peer and its various destinations.
In more detail as it is depicted in Fig. 2 each peer by acting as a sender sends sequentially P2P
blocks (B1-B5). Each one of them is composed from a set of network packets and is heading to a
different receiver peer that belongs in a set of receiver peers (Receiver Peer 1,2 and 3 in Fig. 2).
The delay between the sender and each receiver peer i is different. Each receiver peer i sends
acknowledgement packets. In Fig. 2 delays and acknowledgments are noted as d(i) and ack(i)
respectively. Furthermore between the sender and each of the receivers there is a bottleneck
network point which forwards packets with a dynamic bitrate that we note here as h(t). The
objective of the proposed control strategy is to estimate h(t) and control the size of this queue by
using as feedback the acknowledgements that derived from receiver peers which have different
and variable delays. We highlight here that the traditional congestion control approach is not
functional because of the diversity of these delays.
Figure 2. P2P live streaming network traffic
4. P2P LIVE STREAMING CONGESTION CONTROL ANALYSIS
In order to fulfil the requirements that we described earlier a control algorithm is executed
periodically and ensures the stable congestion control. The proof of its stability is out of the scope
of this work and analysed in detail in [9]. Our congestion control algorithm runs periodically with
a period T. Each time that the algorithm is executed the source injects u(kT) packets in the
network according to Eq. 1.
( ) ( )
1 1
0 0
( ) .1
l l
j j
u kT w u jT ack jT Eqγ
− −
= =
= − −
∑ ∑
6. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
6
Where ack(jT) is the number of packets that sender acknowledges between time instants (j-1)T
and jT. Parameter γ is a constant and its value between 0 and 1 ensures the stability of our
congestion control. As we will analyse later parameter w is the upper limit in which we want to
set the queue size of the bottleneck network node.
In the rest of this section we prove two lemmas with very important practical consequences upon
which the architecture of the proposed control method is based.
Table 1. Notation
Symbol Definition
T Period under which the P2P congestion control algorithm is executed
nT, n Discrete time instant, number of period
u(n) Number of packets that should be injected in the network by the sender during
the n-th period
h(n) Number of packets that forwarded by the bottleneck network point during the
n-th period
y(n) Number of packets that are in the queue of the bottleneck network point at time
instant n
d(n) Delay that queue introduces to a packet that enters to it at time instant n
b(n) Estimated upload bandwidth of the sender at time instant n
yREF Desirable number of packets in the queue
uREF Number of packets that injected in the queue in the equilibrium state in order to
maintain in length yREF
dREF Desirable delay of the queue
s Size in bits of each packet
λ Time interval between the time instant n that control is executed and the time
instant that the last acknowledged packet sent.
hλ(n) Number of packets that the bottleneck network node forwards between time
instants n and n-λ
uλ(n) Νumber of packets that sender sent between time instants n and n-λ
γ Eigenvalue of the controlled system
Lemma 1: If the control method of Eq. 1 is applied to a P2P live streaming system then the queue
length in the bottleneck network node is always upper bounded by the parameter w that can be
initially set.
Proof: Let a sender peer send packets to m receiver peers which we order according to their
delays (RTT), dp, between a packet transmission to a peer p and the reception of its
acknowledgement by the sender, where d1≤ d2≤ …≤dm. As the control algorithm runs periodically
dp can be expressed as npT where np is equal to the ratio dp/T. Now we define as y(kT) the packet
queue length in the bottleneck node at time kT. Initially we have y(0)=0 which is smaller than w.
Thus, in order to prove lemma 1 with induction it suffices to prove that if lemma 1 holds for time
lT, which means that y(lT)<w, then it also holds for time lT+1, which means that y((l+1)T)<w.
The queue length in the bottleneck network node at time instant lT is described from Eq. 2.
( ) ( ) ( )
1 1
0 0
.2
l l
j j
y lT u jT h jT Eq
− −
= =
= −∑ ∑
In Eq. 2 u(kT) is the number of packets send by the peer during the period kT, and so the number
of packets that arrived in the bottleneck node, and h(kT) is the number of packets that were
7. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
7
served from that node during that period. According to the definition of y(nT) in Eq. 2 y((n+1)T)
can be calculated recursively as:
( ) ( ) ( ) ( )( 1) .3y l T y lT u lT h lT Eq+ = + −
If in Eq. 3 we substitute u(lT) with the proposed from Eq. 1 we have:
( )( ) ( ) ( ) ( )
1 1
0 0
1 ( ) .4
l l
j j
y l T y lT w u jT ack jT h lt Eqγ
− −
= =
+ = + − − −
∑ ∑
The sum of the acknowledged packets from t=0 to t=l-1 is equal to the sum of the sums of the
packets that have been acknowledged by each receiver peer during those periods. The sum of the
acknowledgments from a peer p during that period is equal to the packets that have been served
from the bottleneck network node towards p from t=0 to t=l-np-1, since the acknowledgments
from the packets that were served towards p in the period t=l-np-1 to t=l-1 haven’t been received
yet. As described earlier np is the ratio between dp and the period with which we execute our
congestion control algorithm. According to this observation Eq. 4 is reformed as:
( )( ) ( ) ( ) ( ) ( )
11
0 1 0
1 .5
l npl m
p
j p j
y l T y lT w u jT h jT h lT Eqγ λ
− −−
= = =
+ = + − − −
∑ ∑ ∑
In Eq. 5 m is the number of receivers and λp is the number of packets send to p divided by the
sum of all the packets send to all the receivers.
We can split the sum of the packets that the bottleneck network node served from j=0 until j=l-1
into two sums as depicted in Eq. 6. In this equation λ1
p expresses the ratio of packets that were
sent to node p and were served from bottleneck network node from j=0 until j=l-np-1, which have
already been acknowledged (as derived from the definition of np), and λ2
p expresses the ratio of
packets that were sent to node p and were served from bottleneck network node from j= l-np until
j=l-1, which have not acknowledged yet.
( ) ( ) ( )
11 1
1 2
0 1 0 1
.6
l npl m m l
p p
j p j p j l np
h jT h jT h jT Eqλ λ
− −− −
= = = = = −
= +∑ ∑ ∑ ∑ ∑
Now from Eq. 5 by exploiting Eq. 6 we have:
( )( ) ( ) ( ) ( ) ( )
1 1 1
2
0 0 1
1 ( ) .7
p
l l m l
p
j j p j l n
y l T y lT w u jT h jT h jT h lT Eqγ λ
− − −
= = = = −
+ = + − − + −
∑ ∑ ∑ ∑
By using Eq. 2 we have:
( )( ) ( ) ( ) ( )
1
2
1
1 ( ) .8
m l
p
p j l np
y l T y lT w y lT h jT h lT Eqγ λ
−
= = −
+ = + − + −
∑ ∑
By adding and subtracting w in the second part of Eq. 8 we have:
( )( ) ( ) ( )( ) ( ) ( )
1
2
1
1 1 * .9
m l
p
p j l np
y l T w w y lT h jT h lT Eqγ γ λ
−
= = −
+ = − − − − −∑ ∑
8. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
8
From Eq. 9 i)(1-γ) is positive because 0<γ<1 ,ii) w-y(lT) is positive according to our initial
assumption and iii) h(lT) is always non negative, as it represents the packets that bottleneck
network node serves. Thus, we can conclude that y((l+1)T)<w
The practical importance of this theorem is that if the buffer dedicated to these flows in the
bottleneck network node is larger than w, then packet loss will not occur.
Lemma 2: If the control algorithm of Eq. 1 is applied to a P2P live streaming system and w
satisfies the following inequality.
2
1
1
.10
m
max p p
p
w u n Eqλ
γ=
> +
∑
Then the queue length is positive for any time instant l>nm+1, where nm equals to dm/T for the
receiver m which exhibits the greatest latency between the sender and all the potential receivers.
In the above equation umax is the maximum number of packets that can be served by the
bottleneck node in a period T.
Proof: From Eq. 2 and Eq. 8 we can see that y((l=nm+1)T) is positive. If we prove that if y(lT) is
positive then y((l+1)T) is also positive then by induction we have proved Lemma 2.
According to Eq. 8 we have:
( )( ) ( ) ( ) ( ) ( )
1
2
1
1 1 * .11
p
m l
p
p j l n
y l T y lT w h jT h lT Eqγ γ γ λ
−
= = −
+ = − + − −∑ ∑
Where y((l+1)T) is larger than:
( )( ) ( ) ( )
1
2
1
1 .12
m l
p
p j l np
y l T w h jT h lT Eqγ γ λ
−
= = −
+ ≥ − −∑ ∑
But according to our model the maximum number of packets that bottleneck network
point serves is umax so we can rewrite Eq. 12 as:
( )( )
1
2
1
1 .13
m l
p max max
p j l np
y l T w u u Eqγ γ λ
−
= = −
+ ≥ − −∑ ∑
Where the second part of Eq. 13 is:
1
2 2
1 1
1
.14
m l m
p max max max p p
p j l np p
w u u w u n Eqγ γ λ γ λ
γ
−
= = − =
− − = − +
∑ ∑ ∑
The practical importance of this lemma is that we are able to calculate dynamically w
according to the network latencies and the ratio of unacknowledged packets from each
receiver and guarantee in this way that there will not be idle bandwidth resources.
5. DYNAMIC WINDOW CALCULATION
In this section we analyse how it is calculated the window of the proposed P2P congestion
control. Towards this goal we will exploit Lemma 1 and Lemma 2 in order to ensure that the
9. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
9
capacity of the bottleneck network point will not be exceeded and that all the available bandwidth
will be exploited. From Lemma 2, if we choose γ=1 we have:
2 2
1 1
1
( / ) 1 .15
m m
max p p p p
p p
w u T n T U d Eqλ λ
γ= =
> + = +∑ ∑
As described previously, dp is the time between a packet transmission to peer p and the reception
of its acknowledgement by the sender. This time interval is equal to the RTT between the sender
and the receiver when the queue of the bottleneck network point is empty plus the time the packet
has been in this queue (dp=dq+RTTp). dq is 0 when the queue is empty and dqmax when the queue is
full. From this equation we can calculate the delay in the queue dp=dq+RTTp and thus be able to
control it to a point which belongs in the region (0,dqmax), where dpmax=dqmax+RTTp. We note
here that the calculation of dq and dqmax is the same for every receiver peer p and consequently
independent of p. As a result we note as d(kT) the average queue delay that the packets, which
were sent to the various receivers during the kth interval, experienced.
The problem that arises here is the calculation of RTTp and dqmax. Since there is no way to
accurately measure the RTTp we substitute it with dpmin, which is the lowest delay observed for
peer p. In order to calculate dqmax we must observe packet loss due to congestion, in which case
dpmax=dqmax+RTTp where dpmax is the latency of the last packet that has been successfully
transmitted. We now set in Eq. 16 dref which is the queue delay in which we want to operate as a
percentage a of the total queue size. As a result we have:
min max min*( 0 1 .) 16ref p p pd d a d d with Eqα< <= + −
The intuition behind this is that when the peer-to-peer flows start with an empty queue it holds
that RTTp=dpmin, otherwise, when unrelated flows pre-exists we get an inaccurate greater value for
the RTTp. However, this is not a problem since the goals of the proposed congestion control
algorithm are not compromised. By setting dref greater than dpmin we guarantee that there are
always available packets in the queue waiting to be transmitted and thus the available bandwidth
is utilized. Also, by having dref always less than dpmax congestion and packet loss is avoided.
Packet loss will trigger the right estimation of dpmax and so the recalibration of the control leading
to the desired behaviour.
We are now in position to dynamically determine the window size, w(kT), in each iteration of the
congestion control algorithm, according to the Eq.17:
2
2
1
( ) ( ) ( )( _ ) 1 ( ) .17
m
p p ref ref
p
w kT U kT kT d min d T d d kT Eqλ γ
=
= + + + + −
∑
Where U(kT) is the estimated upload bandwidth in the previous interval and λ2
p(kT) is the ratio of
the number of packets transmit to node p and not yet acknowledged to the total number of
transmitted packets in the same interval that are not yet acknowledged.
The intuition behind Eq. 17 is that the first term is derived directly from Lemma 2. The second
term of Eq. 17 namely γ2[dref-d(kT)] becomes positive and increases the window in case that
dref>d(kT) and in this case the queue in the bottleneck network point increases. On the contrary if
dref<d(kT) this second term becomes negative and the queue in the bottleneck network point
decreases. In this way the queue is stabilized to the desired dref.
10. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
10
The value of dref, and more specifically the value of the constant α in Eq. 16, determines the
aggressiveness of the proposed congestion control algorithm towards unrelated TCP traffic. If α is
close to 0 then the congestion control algorithm is not aggressive at all and in case it is co-
existing with TCP it gives priority to the latter. In the opposite case, where α is close to 1, the
algorithm becomes very aggressive with high probability of causing starvation to other TCP
flows. In our future work we will focus to the analytical correlation between the value of the dref
and its effect in case that our P2P congestion control co-exists with TCP.
Finally the value of U(kT) is calculated dynamically by measuring the rate of the arrival of the
acknowledgments during the time interval between kT and kT-tc (i.e. the last tc seconds). If this
interval is small then the congestion control can react very quickly to changes in the available
upload bandwidth but in expense of its stability. This type of calculation is meaningful only when
the queue in non-empty, as otherwise the estimated available bandwidth will be equal to the
sending rate which will be probably smaller than the actual available bandwidth. However, in that
case, as d(kT) will be smaller than dref, the window size will increase, causing an increase in the
sending rate and thus filling the queue and providing meaningful estimation of U(kT).
6. EXPERIMENTATION METHODOLOGY AND EVALUATION
In order to evaluate our proposed system we performed simulations with Opnet [30] and we
implemented and evaluated a real prototype under a variety of scenarios. The development of our
real prototype was facilitated by experimentation and monitoring tools which have been created
by BonFIRE test-bed [10]. Our experimentation scenarios have been set up by using the
infrastructure of iMinds (Virtuall Wall [11]). Virtual Wall is a test bed in which set of nodes are
connected through a virtual network. It gives to the test bed user the capability to create the
desired network topology and dynamically adjust (during the experiments) features of each
underlying network link as: path latency, path bandwidth, packet loss rate, etc. In order to
evaluate the proposed congestion control architecture a network topology has been created in
which a node has been assigned to act as a P2P traffic sender and a set of nodes have been used as
P2P traffic receivers. Another node has been used as router in order to be able to adjust the
features of each network path and to act as the bottleneck network node.
Three sets of experiments were performed in order to prove the properties of the proposed P2P
congestion control. In the first one its robustness to changes in the latency of the underling
network path is demonstrated. In the second is demonstrated its ability to dynamically adapt to
very curt changes bandwidth of the bottleneck network point and in the third its friendliness (co-
existence) to unrelated TCP traffic.
6.1. Path latency variation
The purpose of the first experiment is to demonstrate the robustness of the proposed architecture
to the dynamic changes in the latency of the underlying network paths. In order to achieve this
was created a network topology with two types of network links. The first one is the Sender-
Router (bottleneck network point) link and its latency is set to a constant value equal to 20ms,
while the second one is the Router-Receiver link whose latency changes every 10s according to a
uniform distribution between 2ms and 22ms. The available upload bandwidth is constant and
equal to 4000 Kbps. In this scenario a sender peer sends only to one receiver.
In Figure 3 we depict three variables. The first is Path minimum Round Trip Time, which
changes dynamically during the execution of the experiment, the second is the desired Round
Trip Time, including the time that the packets remained in the queue, and the third represents the
actual measured delay between the transmission of a packet and its acknowledgment. From
11. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
11
Figure 3 we can see that although Path RTT changes very dynamically our architecture stabilizes
the queue size in the bottleneck network node at a value very close to RTTref (dREF+RTT)
without ever exceeding this value. Additionally RTT average is always higher than Path RTT and
never falls so low. These two observations testify that despite the changes in the underlying
network path latency, our architecture fully exploits the available bandwidth without causing
packet loss.
Figure 3. Path minimum Round Trip Time (Path RTT), desired Round Trip Time (RTT ref) and actual
Round Trip Time (RTT avg) over time
Figure 4. Amount of data to be sent, u(kT), and window, w(kT), over time
Figure 4 depicts u(kT) (as it is dynamically calculated from Eq. 1 in each iteration of the
algorithm) along with the w(kT), which is the window that is calculated according to Eq. 17. Both
are multiplied by the packet size in order to be translated from number of packets to Kbits. As
Figure 4 shows, the window increases in the beginning when the measured RTT values are small
and then it remains stable despite the variation of path latency. The spikes in u(kT) testify the
immediate adaptation of our architecture to the changes of path latency.
In Figure 5 are depicted three variables. The first is the a priori set available bandwidth in the
bottleneck network point (available BW). The second is the acknowledgement rate, which is
dynamically measured (ack rate). The third is the calculated upload bandwidth by the sender (U).
12. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
12
Figure 5 demonstrates the ability of the proposed algorithm to calculate with very high accuracy
the available upload bandwidth.
Figure 5. A priori set available bandwidth, acknowledgement rate and measured bandwidth over time
6.2. Path bandwidth variation
In the second set of experiments a sender sequentially sends P2P blocks to multiple receivers
using the network topology of the previous experiment. The difference now is that there are four
receivers connected with four Router-receiver links. The latency of each of these paths is now
configured to the following values: d1=12ms, d2=22ms, d3=7ms and d4=16ms.
For better presentation of the results we define the variable dRTTi, which represents the
difference between the measured latency between the sender and receiver i and the actual RTT
between the sender and i (which is the RTT that was set during the deployment of the network
topology). This variable represents the time interval that the packets, which were transmitted to
node i, remained in the bottleneck queue and ideally should be the same with the value of the dref
control variable.
In the first scenario the upload bandwidth of the sender remains constant and is set to 4Mbps.
Figure 6 shows that the dRTT values for all the receivers are similar and very close to the dref
value, although their respective RTT values are very different. Figure 6 testifies the ability of the
proposed algorithm to control the size of the queue to the preference point during sequential
transmission of P2P block to different network locations.
In the next scenario, which is represented in Figure7, Figure 8 and Figure 9, the available
bandwidth in the router, that acts as the bottleneck network point, changes dynamically every 10
seconds according to a uniform distribution between 1 and 5 Mbps.
Figure 7 depicts how the available bandwidth changes over time and how the proposed P2P
congestion control manages to measure the available upload bandwidth by measuring the rate of
the acknowledgment’s reception.
Figure 8 depicts u(kT) and w(kT) measured in Kbits. It is evident, by inspecting these two
figures, that the proposed P2P congestion control is able to adapt very quickly to these very
abrupt changes of the available bandwidth and to fully exploit it in every time instant.
13. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
13
Figure 6. Queue delay measured through acknowledgements from four different receivers
Figure 7. Available bandwidth, Acknowledge rate and measured bandwidth over time
Figure 8. Amount of data to be sent, u(kT), and window, w[kT], over time
14. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
14
Figure 9. Bottleneck point queue delay as it is dynamically measured from acknowledgements from four
different receivers
Finally, Figure 9 depicts the dRTT values for the different receivers along with the dref control
variable. The interesting thing about this figure, besides the fact that all the dRTT values follow
the behaviour of the dref, is the behavior of the dref variable itself. Although the different actual
RTT values remain the same for all the receivers the dref variable changes over time. This is due
to the recalculation over time of the dpmax variable (Eq. 16). In the beginning there are no errors so
the value of dpmax is calculated by adding a constant to the dpmin variable. However, as the
available bandwidth changes, and more specifically when it drops, packet loss occurs. This
triggers the dynamic recalculation of the dpmax variable and as the result the recalculation of the
dref. This dynamic behaviour of dref along with its advantages will be shown more clearly in the
next set of experiments
6.3. Co-existence with TCP
The third set of experiments analyses the behaviour of the proposed P2P congestion control under
the existence of TCP traffic. In order to take meaningful results two different congestion control
algorithms of TCP were used. These are TCP-BIC [15] and TCP-RENO [16]. The setup for the
remaining experiments is the same with the second set, having four receivers with fixed path
latencies according to the previous distribution. The capacity of the bottleneck node is fixed and
set to 4Mbps. The duration of the experiments is 100s and by using iperf [17] TCP data is sent to
receiver 1 in parallel with the P2P flows. The value of the constant α in Eq. 16 is set to 0.75.
TCP-BIC: In the first experiment, where TCP-BIC coexists with the proposed P2P congestion
control, TCP flow starts after our algorithm has been running for 40s and lasts for 60s. Figure 10,
Figure 11 and Figure 12 are the same three graphs that we presented for the first two set of
experiments .Figure 10 depicts the recalibration of the dref variable. When TCP traffic starts at
time 40 the queue gets full and an error occur. This triggers the right calculation of the dpmax and
thus of the dref. From that point on dref remains constant, meaning there are no more lost packets,
and the congestion control algorithm succeeds in keeping the dRTT values close to the desired
point. Figure 11 and Figure 12 show how the control algorithm adapts to the presence of the TCP
traffic. The u(kT) and w(kT) drops and stabilize in time, while quickly regaining their initial
value after the termination of the TCP traffic. The above experiment depicts the ability of the
proposed P2P congestion control to not starve and to stably continue to send data despite TCP-
BIC trying to push the queue latency (dRTT) to the desired value.
15. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
15
Figure 10. Queue delay measured through acknowledgements from four different receivers
Figure 11. Amount of data to be sent, u(kT), and window, w[kT], over time
Figure 12. A priori set available bandwidth, Acknowledge rate and measured bandwidth over time
16. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
16
Figure 13. Queue delay as it is measured from acknowledgements from four different receivers
Figure 14. Amount of data to be sent, u(kT), and window, w[kT], over time
Figure 15. A priori set available bandwidth, Acknowledge rate and measured
17. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
17
In the second experiment with TCP-BIC which is depicted in Figure 13, Figure 14 and Figure 15
the proposed P2P congestion control architecture is started after the TCP has been running for 30s
(time 0). We can observe that, also in this scenario, the proposed congestion control manages to
“compete” fair with the TCP traffic and allocate half the available bandwidth (2 Mbps), while,
when the TCP flow ends (time 30s), it quickly adjusts and uses all the available which is 4Mbps
TCP-RENO: The TCP-RENO experiment is identical with TCP-BIC experiment. Figure 16,
Figure 17 and Figure 18 depict the case that TCP traffic started at 15 sec and ended at 75sec. As
TCP-RENO doesn’t behave as aggressively as TCP-BIC, the allocated bandwidth of the P2P
congestion control quickly converges at 2Mbps, which is half the capacity of the link.
In the second TCP-RENO experiment, P2P traffic started after the TCP stream has been running
for 25s. In Figure 19, Figure 20 and Figure 21 we see how P2P congestion control tends to
converge around 3Mbps.
Figure 16. Bottleneck point queue delay as it is dynamically measured from acknowledgements from four
different receivers
Figure 17. Amount of data to be sent, u(kT), and window, w[kT], over time.
18. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
18
Figure 18. A priori set available bandwidth, Acknowledge rate and measured bandwidth over time
Figure 19. Queue delay as it is measured from acknowledgements from four different receivers
Figure 20. Amount of data to be sent, u(kT), and window, w[kT], over time.
19. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
19
Figure 21. Available bandwidth, Acknowledge rate and measured bandwidth over time
6. CONCLUSIONS
Traditional congestion control algorithms are designed for bulk point to point transfers. In this
work we designed, implemented and evaluated a P2P congestion control algorithm suitable for
flows containing small chunks of data which are transmitted sequentially to different network
destinations. Our theoretical work was justified though our evaluation in a real and implemented
system and we proved that our proposed P2P congestion control architecture: i) is able to utilize
efficiently all the upload bandwidth of participating peers, ii) is stable, robust even under sudden
and large and changes in the bandwidth of the bottleneck network point, iii) is immune to time-
varying delays (underlying path latency) caused by dynamic underlying network traffic, iv) is
able to measure accurately and dynamically the upload bandwidth capacity of each peer, v) is
able, by controlling the queue length in the bottleneck network point, to avoid buffer overloading
in the Home Gateways and routers of the underlying network.
ACKNOWLEDGEMENTS
This work was funded from BonFIRE [10] which is an EU project funded by the EC FP7 under
grant agreement number 257386.
REFERENCES
[1] Konstantinos Deltouzos, Ilias Gkortsilas, Nikolaos Efthymiopoulos, Spyros Denazis, (2013)
“Liquidstream II - Scalable P2P overlay optimization with adaptive minimal server assistance for
stable and efficient Video On Demand”, In IEEE INFOCOM
[2] Efthymiopoulos N, Christakidis A, Denazis S, Koufopavlou O. (2011) “Liquidstream – network
dependent dynamic P2P live streaming”, Springer Peer-to-Peer Networking and Applications
[3] Christakidis A, Efthymiopoulos N, Fiedler J, Dempsey S, Koutsopoulos K, Denazis S, Tombros S,
Garvey S,Koufopavlou O. (2011) “VITAL++ a new communication paradigm: embedding P2P
technology in next generation networks”, IEEE Communications Magazine
[4] Yang, Y, A.L.H. Chow, L. Golubchik and D. Bragg, (2010) “Improving QoS in BitTorrent-like VoD
Systems”, In IEEE INFOCOM
[5] Delia Ciullo, Valentina Martina, Michele Garetto, Emilio Leonardi, Giovanni Luca Torrisi. (2012)
“Stochastic Analysis of Self-Sustainability in Peer-Assisted VoD Systems”, In IEEE INFOCOM
20. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
20
[6] “PPLive, http://www.gridcast.cn/. GridCast, http://www.gridcast.cn/. PPStream,
http://www.ppstream.com/. TVU, http://www.tvunetworks.com/. SopCast, http://www.sopcast.com/.”
[7] “Cisco 2015, Visual Networking Index (VNI), The Zettabyte Era—Trends and Analysis
(http://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-
vni/VNI_Hyperconnectivity_WP.html)
[8] Delia Ciullo, Valentina Martina, Michele Garetto, Emilio Leonardi, Giovanni Luca Torrisi, (2012)
“Performance Analysis of Non-stationary Peer-assisted VoD Systems”. In IEEE INFOCOM
[9] Ignaciuk Przemysław, Bartoszewicz Andrzej, (2013), “Congestion Control in Data Transmission
Networks, Springer”, ISBN 978-1-4471-4147-1
[10] “BonFIRE”, http://www.bonfire-project.eu/
[11] “iMinds” Virtual Wall, http://www.iminds.be/en/develop-test/ilab-t/virtual-wall
[12] R. Birke, C. Kiraly, E. Leonardi, M. Mellia3, M. Meo, S. Traverso, (2012) “Hose Rate Control for
P2P-TV Streaming Systems”, Elsevier Computer Communications Vol. 35, Issue 18, pp. 2237–2244
[13] S. Shalunov and G. Hazel, 2010 “Low Extra Delay Background Transport (LEDBAT),” IETF,
Internet Draft draft-ietf-ledbat-congestion-02
[14] Phil. Trans. Birke, R. ; Leonardi, E.; Mellia, M.; Bakay, A.; Szemethy, T. ; Kiraly, C.,Lo Cigno, R. ;
Mathieu, F. ; Muscariello, L. ; Niccolini, S. ; Seedorf, J. ; Tropea,G, (2011) “Architecture of a
network-aware P2P-TV application: the NAPA-WINE approach”, IEEE Communications Magazine,
Vol 49, Issue 6, 2011
[15] “TCP-BIC”, http://www4.ncsu.edu/~rhee/export/bitcp.pdf
[16] “TCP-RENO”, http://tools.ietf.org/html/rfc3782
[17] “Iperf”, http://sourceforge.net/projects/iperf/
[18] Maria Efthymiopoulou, Nikolaos Efthymiopoulos, Athanasios Christakidis, Spyros Denazis,
Odysseas Koufopavlou, (2014) “Scalable control of bandwidth resources in P2P live streaming”, In:
Proceedings of 22nd Mediterranean Conference of Control and Automation (MED), IEEE, pp.792-
797
[19] Maria Efthymiopoulou, Nikolaos Efthymiopoulos, Athanasios Christakidis, Nikolaos
Athanasopoulos, Spyros Denazis, Odysseas Koufopavlou, (2015) “Scalable playback rate control in
P2P live streaming systems” Springer , Peer-to-peer Networking and Applications, 2015 (accepted)
[20] H Zhang, J Wang, M Chen, K Ramchandran (2009) Scaling Peer-to- Peer Video-on-Demand
Systems Using Helpers. In:Proceedings of the IEEE 16th Int. Conf. on Image Processing. IEEE, pp.
3053-3056
[21] J Wang, C Yeo, V Prabhakaran, K Ramchandran (2007) On the role of helpers in Peer-to-Peer file
download systems: Design, analysis and simulation. In: Proceedings of the 6th Int. Workshop on
Peer-To-Peer Syst. (IPTPS 2007)
[22] R Sweha, V Ishakian, A Bestavros (2012) Angelcast: cloud-based peerassisted live streaming using
optimized multi-tree construction. In: Proceedings of the 3rd Multimedia Systems Conference. ACM,
pp. 191–202
[23] P Michiardi, D Carra, F Albanese, A Bestavros (2012) Peer-assisted content distribution on a budget.
ELSEVIER Computer Networks 56(7):2038–2048
[24] H Kavalionak ,A Montresor (2012) P2P and cloud: A marriage of convenience for replica
management. In: Proceedings of the 6th IFIP Int. Workshop on Self-Organizing Systems, ser. Lecture
Notes in Computer Science. Springer, pp. 60–71
[25] UUSee, [Online]. Available: http://www.uusee.com
[26] Y Chen, B Zhang, C Chen, D M Chiu (2014) Performance modeling and evaluation of peer-to-peer
live streaming systems under flash crowds. IEEE/ACM Trans Netw 22(4):1106–1120
[27] N Magharei, R Rejaie, I Rimac, V Hilt, M Hofmann (2014) Isp-friendly live p2p streaming.
IEEE/ACM Trans Netw 22(1):244–256
[28] C Wu, B Li, S Zhao (2012) Diagnosing Network-wide P2P Live Streaming Inefficiencies. ACM
Trans multimedia Comput. Commun. Appl. 8(1S):Article 13
[29] A Payberah, H Kavalionak, V Kumaresan, A Montresor, S Haridi (2012) Clive: Cloud-Assisted p2p
Live Streaming. In: Proceedings of 12th Int. Conf. Peer-to-Peer Computing. IEEE, pp. 79–90
[30] Opnet modeler, [Online]. Available: www.opnet.com
21. International Journal of Peer to Peer Networks (IJP2P) Vol.6, No.2, August 2015
21
AUTHORS
Nikolaos Efthymiopoulos received the diploma and Doctor of Philosophy degree in
Electrical and Computer Engineering from the University of Patras, Greece, in 2004 and
2010, respectively. His main research interests are: network optimization, network
control, scalable systems, peer to peer, distributed video streaming, distributed searching
and achieving QoS in computer networks. He has more than 20 publications in these
areas. He more than 10 years of experience in several FP7 ICT projects and he was
technical manager assistant and WP leader in VITAL++ and STEER. He has temporarily
worked as an Assistant Professor in Informatics & MM Department in Greece. He is
currently a Post-Doctoral Research Associate at the University of Patras in Greece.
Athanasios Christakidis received his diploma in 2004 and his Doctor of Philosophy in
2010 from the Department of Electrical and Computer Engineering at the University of
Patras, Greece. His research interests are peer to peer networks, distributed optimization,
network resource allocation, and congestion control. Since 2004, he participated in several
FP7 projects, and he has more than 15 publications in these areas. He has led the
development of a client for stable and efficient peer to peer live streaming.
Maria Efthymiopoulou received the first degree and the Doctor of Philosophy degree in
Electrical and Computer Engineering from the University of Patras, Greece, in 2008 and
2015, respectively. Her main research interests are: network control, scalable systems, peer
to peer, live streaming, video on demand, development of simulation environments, QoS in
computer networks. She has several publications in these areas. She has 7 years of
experience in several FP7 ICT projects. She is currently a Post-Doctoral Research
Associate at the University of Patras in Greece.
Loris Corazza was born in Italy on 1982. He approached to University of Patras as
member of the Network Architectures and Management group in 2009. His involvement in
ICT projects started in 2008, when he was member of the Smart Systems Team in Hitachi
SAS Sophia-Antipolis Research Lab. He has been one of the head developers of P2NER
P2P-Client while researching in the area of P2P Systems and Content Distribution
Networks. He is currently a researcher at University of Patras, Greece in the area of Optical
Software Defined Networks. His main interests and expertise are: software design and
architecture, network protocols, network management, algorithms for data distribution in P2P networks and
performance evaluation, network security.
Spyros Denazis is a Professor in the Electrical & Computer Engineering Department, at the
University of Patras, Greece. He received his Doctor of Philosophy in Computer Science
from the University of Bradford, UK, in 1993. In 1996, he joined the R&D Department of
Intracom SA in Athens as Project Coordinator, and in 1998, he joined the Information
Technology Laboratory of Hitachi Europe in Cambridge UK, as a Senior Research Engineer
while serving for 3 years (1998-2001) as an Industrial Research Fellow in the Centre for
Communications Systems Research , of Cambridge University, UK. For the period 2003-
2010, he had also been a Consultant for the Hitachi Europe Sophia Antipolis Laboratory, in France.
Currently, he leads the Network Architecture & Management Group where he coordinates a range of
research activities in the areas of P2P live streaming, future internet research experimentation, and SDN.