Weihua Sun, Naoki Shibata, Keiichi Yasumoto, Masaaki Mori, "A Method for Overlay Network Latency Estimation from Previous Observation", in Proc. of The Twelfth International Conference on Networks (ICN2013), pp.95--100, 29 Jan. 2013.
Abstract—Estimation of the qualities of overlay links is useful for optimizing overlay networks on the Internet. Existing estimation methods requires sending large quantities of probe packets between two nodes, and the software for measurements have to be executed at both of the end nodes. Accurate measurements require many probe packets to be sent, and other communication can be disrupted by significantly increased network traffic. In this paper, we propose a link quality estimation method based on supervised learning from the previous observation of other similar links. Our method does not need to exchange probe packets, estimation can be quickly made to know qualities of many overlay links without wasting bandwidth and processing time on many nodes. We conducted evaluation of our method on PlanetLab, and our method showed better performance on path latency estimation than estimating results from geographical distance between the two end nodes.
Developing QoS by Priority Routing for Real Time Data in Internet of Things (...IJCNCJournal
In networks, many application protocols such as CoAP, REST, XMPP ,AMQP have been proposed for IoT communication which includes p2p or S2S. In MANET Network convergence does the way for improvements in Internet of Things (IoT) communication with high potential for a wide range of applications. Each protocol focuses on some aspects of communication in the IoT. Hence, these application protocols have indicated of how IoT has integrated to enhanced and developed of a new service that require to guarantees
the wide range offered by the quality of services. In this paper, we will introduce a smart pathway that can be bridge the gap between IoT services with its real data traffic. Therefore, we enhanced the MANET routing protocol for computing two or more paths to pass the more that one high priority real traffic data via these paths to improve the gloomy picture of this protocol in the context of IoT. In particular, the good services
with high timely delivery of urgent data such as real time data environmental monitoring. After surveying the published and available protocol interoperability given for urban sensing. In this research, we have proposed a novel solution to integrate MANET overlays, and collaboratively formed over MANET, to boost urban data in IoT. Overlays are used to dynamic differentiate and fasten the delivery of high priority real application time data over low-latency MANET paths by integrating with the original specifications. Our experimental results showed the effectiveness on the network such as the overhead and network congestion. In addition, the initial
results of the light-weight improved the routing protocol over the baseline protocols in terms of the delay of reciveing the packets between nodes which lead to increase the throughput by reducing loss packets.
Comprehensive Path Quality Measurement in Wireless Sensor NetworksIJTET Journal
A wireless sensor network mostly relies on multi-hop transmissions to deliver a data packet. It is of essential importance to measure the quality of multi-hop paths and such information shall be utilized in designing efficient routing strategies. Existing metrics like ETF, ETX mainly focus on quantifying the link performance in between the nodes while overlooking the forwarding capabilities inside the sensor nodes. By combining the QoF measurements within a node and over a link, we are able to comprehensively measure the intact path quality in designing efficient multihop routing protocols. We propose QoF, Quality of Forwarding, a new metric which explores the performance in the gray zone inside a node left unattended in previous studies. We implement QoF and build a modified Collection Tree Protocol.
Impact of energy and link quality indicator with link quality estimators in w...graphhoc
The Link Quality Indicator (LQI) and Residual Energy have a fundamental impact on the network
performance in Wireless Sensor Networks (WSNs) and affects as well in the life time of nodes. This paper
will provide a comparative of Link Quality Estimator, the Link Quality Estimator with Link Quality
Indicator and Link Quality Estimator with Residual Energy. In this paper we develop a Collect Tree
Protocol (CTP) and compare the performance of LQI and Residual Energy, and show their effect on the
packet delivery ratio and throughput, covering the characteristics of low-power links, and their
performance to the best of our knowledge, we believe that our efforts would have implementations on
embedded application.
The International Journal of Engineering and Science (The IJES)theijes
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.
Developing QoS by Priority Routing for Real Time Data in Internet of Things (...IJCNCJournal
In networks, many application protocols such as CoAP, REST, XMPP ,AMQP have been proposed for IoT communication which includes p2p or S2S. In MANET Network convergence does the way for improvements in Internet of Things (IoT) communication with high potential for a wide range of applications. Each protocol focuses on some aspects of communication in the IoT. Hence, these application protocols have indicated of how IoT has integrated to enhanced and developed of a new service that require to guarantees
the wide range offered by the quality of services. In this paper, we will introduce a smart pathway that can be bridge the gap between IoT services with its real data traffic. Therefore, we enhanced the MANET routing protocol for computing two or more paths to pass the more that one high priority real traffic data via these paths to improve the gloomy picture of this protocol in the context of IoT. In particular, the good services
with high timely delivery of urgent data such as real time data environmental monitoring. After surveying the published and available protocol interoperability given for urban sensing. In this research, we have proposed a novel solution to integrate MANET overlays, and collaboratively formed over MANET, to boost urban data in IoT. Overlays are used to dynamic differentiate and fasten the delivery of high priority real application time data over low-latency MANET paths by integrating with the original specifications. Our experimental results showed the effectiveness on the network such as the overhead and network congestion. In addition, the initial
results of the light-weight improved the routing protocol over the baseline protocols in terms of the delay of reciveing the packets between nodes which lead to increase the throughput by reducing loss packets.
Comprehensive Path Quality Measurement in Wireless Sensor NetworksIJTET Journal
A wireless sensor network mostly relies on multi-hop transmissions to deliver a data packet. It is of essential importance to measure the quality of multi-hop paths and such information shall be utilized in designing efficient routing strategies. Existing metrics like ETF, ETX mainly focus on quantifying the link performance in between the nodes while overlooking the forwarding capabilities inside the sensor nodes. By combining the QoF measurements within a node and over a link, we are able to comprehensively measure the intact path quality in designing efficient multihop routing protocols. We propose QoF, Quality of Forwarding, a new metric which explores the performance in the gray zone inside a node left unattended in previous studies. We implement QoF and build a modified Collection Tree Protocol.
Impact of energy and link quality indicator with link quality estimators in w...graphhoc
The Link Quality Indicator (LQI) and Residual Energy have a fundamental impact on the network
performance in Wireless Sensor Networks (WSNs) and affects as well in the life time of nodes. This paper
will provide a comparative of Link Quality Estimator, the Link Quality Estimator with Link Quality
Indicator and Link Quality Estimator with Residual Energy. In this paper we develop a Collect Tree
Protocol (CTP) and compare the performance of LQI and Residual Energy, and show their effect on the
packet delivery ratio and throughput, covering the characteristics of low-power links, and their
performance to the best of our knowledge, we believe that our efforts would have implementations on
embedded application.
The International Journal of Engineering and Science (The IJES)theijes
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.
Hexagonal based Clustering for Reducing Rebroadcasts in Mobile Ad Hoc NetworksIJTET Journal
Abstract— In mobile ad hoc networks multihop routing is performed in order to communicate the packets from the source to destination. The nodes within these networks are dynamic due which frequent path change occurs which can cause frequent link breakages and induces route discoveries. These route discoveries can introduce overhead in terms of contention, collision and rebroadcasts which are non-negligible. Here, the paper discusses a hexagonal based clustering for reducing rebroadcasts thus maximizing the lifetime of the networks and providing coverage area thus reducing the end – end delays.
DOTNET 2013 IEEE MOBILECOMPUTING PROJECT Optimal multicast capacity and delay...IEEEGLOBALSOFTTECHNOLOGIES
To Get any Project for CSE, IT ECE, EEE Contact Me @ 09849539085, 09966235788 or mail us - ieeefinalsemprojects@gmail.com-Visit Our Website: www.finalyearprojects.org
Congestion in Wireless Sensor Networks has negative impact on the Quality of Service.
Congestion effects the performance metrics, namely throughput and per-packet energy
consumption, network lifetime and packet delivery ratio. Reducing congestion allows better
utilization of the network resources and thus enhances the Quality of Service metrics of the
network. Traffic Aware Dynamic Routing to Alleviate Congestion in Wireless Sensor Networks
reduces congestion by considering one hop neighbor routing in the network. This paper
proposed an algorithm for Quality of Service Based Traffic-Aware Data forwarding for
congestion control in wireless sensor networks based on two hop neighbor information. On
detection of congestion, the algorithm forwards data packets around the congestion areas by
spreading the excessive packets through multiple paths. The path with light load or under
loaded nodes is efficiently utilized whenever congestion occurs. The main aspect of the
algorithm is to build path to the destination using two independent potential fields depth and
queue length. Queue length field solves the traffic-aware problem. Depth field creates a
backbone to forward packets to the sink. Both fields are combined to yield a hybrid potential
field to make dynamic decision for data forwarding. Network Simulator used for simulating the
algorithm is NS2. The proposed algorithm performs better.
Destination Aware APU Strategy for Geographic Routing in MANETEditor IJCATR
In this paper, we have explained the Enhanced Adaptive Position Update strategy for geographic routing in mobile ad hoc
network In Adaptive Position Update strategy, there are two techniques: Mobility prediction rule and On-demand learning rule. Proposed
system is based on the destination aware routing in which path to transfer the data over the network is based on the distance from highly
stable node to the destination node. Results of the proposed system are compared with Periodic Beaconing on the basis of packet delivery
ratio, beacon overhead, energy consumption. Experiment results show a high improvement in results on the parameters energy
consumption, packet delivery ratio and beacon overhead. Proposed work is implemented on the NS2 (Network Simulator) Environment
to perform experiments.
Enhance the Throughput of Wireless Network Using Multicast RoutingIOSR Journals
Wireless Mesh Network is designed static or limited mobility environment .In multicast routing for
wireless mesh networks has focused on metrics that estimate link quality to maximize throughput
andtoprovide secure communication. Nodes must collaborate in order to compute the path metric and
forward data.Node identify the novel attacks against high- throughput multicast protocols in wireless
mesh network.. The attacks exploit the local estimation and global aggregation of the metric to allow
attackers to attract a large amount of traffic These attacks are very effective b a s e d on high
throughput metrics. The aggressive path selection is a double-edged sword: It is maximizes throughput,
it also increases attack effectiveness. so Rate guard mechanism will be used.Rate guard mechanism
means combines Measurement-based detection and accusation-based reaction techniques.The attacks
and the defense using ODMRP, a representative multicast protocol for wireless mesh networks, and
SPP, an adaptation of the well-known ETX unicast metric to the multicast setting
Rate Adaptation for Time Varying Channels Using Distributed Relay Selectionpaperpublications3
Abstract: Fixed systems used in cooperative communication suffer from multiplexing loss and low spectral efficiency due to the half duplex constraint of relays. To improve the multiplexing gain, successive relaying is proposed. This allows concurrent transmission of the source and relays. However, the severe inter-relay interference becomes a key challenge. Here Rate Adaptation for Time Varying Channels Using Distributed Relay Selection is proposed, which is capable of adapting the relay’s rate using distributed relay selection.
Dear Students
Ingenious techno Solution offers an expertise guidance on you Fianal Year IEEE & Non- IEEE Projects on the following domain
JAVA
.NET
EMBEDDED SYSTEMS
ROBOTICS
MECHANICAL
MATLAB etc
For further details contact us : http://mailto:enquiry@ingenioustech.in 044-42046028 or 8428302179.
we are located in the following venue:
Ingenious Techno Solution
#241/85, 4th floor
Rangarajapuram main road,
Kodambakkam (Power House)
http://www.ingenioustech.in/
A MANET is a continuously self-configuring, infrastructure-less type network, which consists of number of mobile nodes
with wireless network interfaces. In order to make communication among nodes, the nodes demoniacally establish paths among
neighbouring nodes. Security in mobile adhoc network is a big challenge because many nodes perform many kinds of misbehaviour.
In this paper, the main focus is on collaborative attacks in MANET using CBDS approach. CBDS is a approach which consolidate
asset of proactive and reactive defense method in reverse tracing. In reverse tracing method we compare performance of CBDS
approach with DSR and AOMDV routing protocols.
Summit 16: Achieving Low Latency Network Function with OpnfvOPNFV
It's challenging to have low-latency VNFs in virtualization and cloud environment. OPNFV KVM4NFV project, together with other OPNFV projects like OVSNFV, helps to achieve low latency network functionality. This session will firstly introduce KVM4NFV project. Then some DPDK workload will be used to show how the KVM4NFV project helps reducing the packet latency and compare the result with and without OPNFV environment. In the end, experience will be shared on how to setup the OPNFV environment correctly, and how to tune the OPNFV environment to meet the latency and performance requirement.
Hexagonal based Clustering for Reducing Rebroadcasts in Mobile Ad Hoc NetworksIJTET Journal
Abstract— In mobile ad hoc networks multihop routing is performed in order to communicate the packets from the source to destination. The nodes within these networks are dynamic due which frequent path change occurs which can cause frequent link breakages and induces route discoveries. These route discoveries can introduce overhead in terms of contention, collision and rebroadcasts which are non-negligible. Here, the paper discusses a hexagonal based clustering for reducing rebroadcasts thus maximizing the lifetime of the networks and providing coverage area thus reducing the end – end delays.
DOTNET 2013 IEEE MOBILECOMPUTING PROJECT Optimal multicast capacity and delay...IEEEGLOBALSOFTTECHNOLOGIES
To Get any Project for CSE, IT ECE, EEE Contact Me @ 09849539085, 09966235788 or mail us - ieeefinalsemprojects@gmail.com-Visit Our Website: www.finalyearprojects.org
Congestion in Wireless Sensor Networks has negative impact on the Quality of Service.
Congestion effects the performance metrics, namely throughput and per-packet energy
consumption, network lifetime and packet delivery ratio. Reducing congestion allows better
utilization of the network resources and thus enhances the Quality of Service metrics of the
network. Traffic Aware Dynamic Routing to Alleviate Congestion in Wireless Sensor Networks
reduces congestion by considering one hop neighbor routing in the network. This paper
proposed an algorithm for Quality of Service Based Traffic-Aware Data forwarding for
congestion control in wireless sensor networks based on two hop neighbor information. On
detection of congestion, the algorithm forwards data packets around the congestion areas by
spreading the excessive packets through multiple paths. The path with light load or under
loaded nodes is efficiently utilized whenever congestion occurs. The main aspect of the
algorithm is to build path to the destination using two independent potential fields depth and
queue length. Queue length field solves the traffic-aware problem. Depth field creates a
backbone to forward packets to the sink. Both fields are combined to yield a hybrid potential
field to make dynamic decision for data forwarding. Network Simulator used for simulating the
algorithm is NS2. The proposed algorithm performs better.
Destination Aware APU Strategy for Geographic Routing in MANETEditor IJCATR
In this paper, we have explained the Enhanced Adaptive Position Update strategy for geographic routing in mobile ad hoc
network In Adaptive Position Update strategy, there are two techniques: Mobility prediction rule and On-demand learning rule. Proposed
system is based on the destination aware routing in which path to transfer the data over the network is based on the distance from highly
stable node to the destination node. Results of the proposed system are compared with Periodic Beaconing on the basis of packet delivery
ratio, beacon overhead, energy consumption. Experiment results show a high improvement in results on the parameters energy
consumption, packet delivery ratio and beacon overhead. Proposed work is implemented on the NS2 (Network Simulator) Environment
to perform experiments.
Enhance the Throughput of Wireless Network Using Multicast RoutingIOSR Journals
Wireless Mesh Network is designed static or limited mobility environment .In multicast routing for
wireless mesh networks has focused on metrics that estimate link quality to maximize throughput
andtoprovide secure communication. Nodes must collaborate in order to compute the path metric and
forward data.Node identify the novel attacks against high- throughput multicast protocols in wireless
mesh network.. The attacks exploit the local estimation and global aggregation of the metric to allow
attackers to attract a large amount of traffic These attacks are very effective b a s e d on high
throughput metrics. The aggressive path selection is a double-edged sword: It is maximizes throughput,
it also increases attack effectiveness. so Rate guard mechanism will be used.Rate guard mechanism
means combines Measurement-based detection and accusation-based reaction techniques.The attacks
and the defense using ODMRP, a representative multicast protocol for wireless mesh networks, and
SPP, an adaptation of the well-known ETX unicast metric to the multicast setting
Rate Adaptation for Time Varying Channels Using Distributed Relay Selectionpaperpublications3
Abstract: Fixed systems used in cooperative communication suffer from multiplexing loss and low spectral efficiency due to the half duplex constraint of relays. To improve the multiplexing gain, successive relaying is proposed. This allows concurrent transmission of the source and relays. However, the severe inter-relay interference becomes a key challenge. Here Rate Adaptation for Time Varying Channels Using Distributed Relay Selection is proposed, which is capable of adapting the relay’s rate using distributed relay selection.
Dear Students
Ingenious techno Solution offers an expertise guidance on you Fianal Year IEEE & Non- IEEE Projects on the following domain
JAVA
.NET
EMBEDDED SYSTEMS
ROBOTICS
MECHANICAL
MATLAB etc
For further details contact us : http://mailto:enquiry@ingenioustech.in 044-42046028 or 8428302179.
we are located in the following venue:
Ingenious Techno Solution
#241/85, 4th floor
Rangarajapuram main road,
Kodambakkam (Power House)
http://www.ingenioustech.in/
A MANET is a continuously self-configuring, infrastructure-less type network, which consists of number of mobile nodes
with wireless network interfaces. In order to make communication among nodes, the nodes demoniacally establish paths among
neighbouring nodes. Security in mobile adhoc network is a big challenge because many nodes perform many kinds of misbehaviour.
In this paper, the main focus is on collaborative attacks in MANET using CBDS approach. CBDS is a approach which consolidate
asset of proactive and reactive defense method in reverse tracing. In reverse tracing method we compare performance of CBDS
approach with DSR and AOMDV routing protocols.
Summit 16: Achieving Low Latency Network Function with OpnfvOPNFV
It's challenging to have low-latency VNFs in virtualization and cloud environment. OPNFV KVM4NFV project, together with other OPNFV projects like OVSNFV, helps to achieve low latency network functionality. This session will firstly introduce KVM4NFV project. Then some DPDK workload will be used to show how the KVM4NFV project helps reducing the packet latency and compare the result with and without OPNFV environment. In the end, experience will be shared on how to setup the OPNFV environment correctly, and how to tune the OPNFV environment to meet the latency and performance requirement.
(BIZ305) Case Study: Migrating Oracle E-Business Suite to AWS | AWS re:Invent...Amazon Web Services
With the maturity and breadth of cloud solutions, more enterprises are moving mission-critical workloads to the cloud. American Commercial Lines (ACL) recently migrated their Oracle ERP to AWS. ERP solutions such as Oracle E-Business Suite require specific knowledge in mapping AWS infrastructure to the specific configurations and needs of running these workloads. In this session, Apps Associates and ACL walk through the considerations for running Oracle E-Business Suite on AWS, including deployment architectures, concurrent processing, load balanced forms and web services, varying database transactional workloads, and performance requirements, as well as security and monitoring aspects. ACL shares their experiences and business drivers in making this transition to AWS.
Principles and Practices in Continuous Deployment at EtsyMike Brittain
Presented at ALM Forum 2014.
Like what you've read? We're frequently hiring for a variety of engineering roles at Etsy. If you're interested, drop me a line or send me your resume: mike@etsy.com.
http://www.etsy.com/careers
Link Prediction And Link Establishment Based On Network Nodes Life Time In Mo...inventionjournals
In this paper we propose a new modified adhoc routing algorithm for adhoc network that locally repairs a link failure and also conflicts the noise and link modification simultaneously. Due to topology changes caused by nodes’ mobility in adhoc network, the link routes get disconnected frequently. Our proposed scheme does a local repair of link failure and also takes care of malicious nodes with the help of a reliability measure while performing route discovery using link-prediction routing algorithm(LPRA). These two performance metrics are integrated by Route link-prediction algorithm. This algorithm is carried out as follows, Select the least dynamic route link with the longest lifetime for persistent data forwarding. Node Lifetime and link lifetime prediction methods. The receiver can measure the signal strength when it receives the packets from sender in same power level and then it calculates the distance between two nodes by applying the radio propagation model in LPRA using adhoc network. Simulation results show that our proposed schemeperforms better in comparison to a popular existing technique
A comparative study in wireless sensor networksijwmn
Sensor networks consist of a large number of small, low-powered wireless nodes with limited computation,
communication, and sensing abilities, in a battery-powered sensor network, energy and communication
bandwidth are a precious resources. Thus, there is a need to adapt the networking process to match the
application in order to minimize the resources consumed and extend the life of the network. In this paper,
we introduce a comparative study in different routing algorithms that propose vital solutions to the most
important issues that should be taken into account when designing wireless network which are reliability,
lifetime, communication bandwidth, transmission rand, and finally the limited energy issue, so we will
introduce their algorithms and discuss how did they propose to solve such of these challenges and finally
we will do some evaluation to each approach.
CONGESTION AWARE LINK COST ROUTING FOR MANETSIJCNCJournal
Due to the dynamic topology, self-configuration and decentralized nature of Mobile Ad hoc Network
(MANET), it provides many benefits in wireless networks and is easy to deploy. But the transmission of
data over ad hoc networks has elevated many technical issues for successful routing. Congestion is one of
the important issues which cause performance degradation of a network, due to long delay and high packet
loss. This paper proposes a Congestion aware Link Cost Routing for MANET where the protocol finds a
path with optimized linked cost based on SNR, Link delay, and the and remaining battery power. Along
with this optimization, in this protocol, every node finds its congestion status and participates in the route
discovery on the basis of its status. Data forwarding is also done based on the congestion status at the time
of forwarding. The protocol results in better performance in terms of packet delivery fraction, end to end
delay, throughput, and packet drop when compared to existing protocols.
Dear Students
Ingenious techno Solution offers an expertise guidance on you Final Year IEEE & Non- IEEE Projects on the following domain
JAVA
.NET
EMBEDDED SYSTEMS
ROBOTICS
MECHANICAL
MATLAB etc
For further details contact us:
enquiry@ingenioustech.in
044-42046028 or 8428302179.
Ingenious Techno Solution
#241/85, 4th floor
Rangarajapuram main road,
Kodambakkam (Power House)
http://www.ingenioustech.in/
Wireless Sensor Network Using Six Sigma Multi Hop RoutingIOSR Journals
Abstract: The most significant problem in the design of wireless sensor networks is to coordinate the sensors with dynamism into a wireless communication network and route sensed data to the base station. The energy efficiency is the most important key point of the network routing designing. This paper presents the efficient multi hop routing algorithm to extend the lifetime of sensor networks and focuses by employing six sigma principles to obtain the Quality of Service. To attain QoS support, we have to find either a route to assure the application requirements or offering network response to the application when the requirements cannot be met. Keywords: Wireless Sensor Networks, Multi hop routing, six sigma, QoS
Wireless Sensor Network Using Six Sigma Multi Hop RoutingIOSR Journals
The most significant problem in the design of wireless sensor networks is to coordinate the sensors
with dynamism into a wireless communication network and route sensed data to the base station. The energy
efficiency is the most important key point of the network routing designing. This paper presents the efficient
multi hop routing algorithm to extend the lifetime of sensor networks and focuses by employing six sigma
principles to obtain the Quality of Service. To attain QoS support, we have to find either a route to assure the
application requirements or offering network response to the application when the requirements cannot be met.
Authentication of Secure Data Transmission In Wireless RoutingIJERA Editor
The major objective of our work is to explore a security enhanced dynamic routing algorithm based on distributed routing information widely supported in existing wired and wireless networks. The message authentication is the main area to be considered in WSN’s. Most of the wireless networks are attacked for detecting the data’s that are transmitted in between the users. We aim at the randomization of delivery paths for data transmission to provide considerably small path similarity (i.e., the number of common links between two delivery paths) of two consecutive transmitted packets. The proposed algorithm should be easy to implement and compatible with popular routing protocols, such as the Routing Information Protocol (RIP) for wired networks and Destination-Sequenced Distance Vector (DSDV) protocol for wireless networks over existing infrastructures. These protocols shall not increase the number of control messages if the proposed algorithm is adopted. An analytic study will be presented for the proposed routing algorithm, and a series of simulation study will be conducted to verify the analytic results and to show the capability of the proposed algorithm.
A scalable and power efficient solution for routing in mobile ad hoc network ...ijmnct
Mobile Ad Hoc Network (MANET) is a very dynamic and infrastructure-less ad hoc network. The actual
network size depends on the application and the protocols developed for the routing for this kind of
networks should be scalable. MANET is a resource limited network and therefore the developed routing
algorithm for packet transmission should be power and bandwidth efficient. These kinds of dynamic
networks should operate with minimal management overhead. The management functionality of the
network increases with number of nodes and reduces the performance of the network. Here, in this paper,
we have designed all identical nodes in the cluster except the cluster head and this criterion reduces the
management burden on the network. Graph theoretic routing algorithm is used to develop route for packet
transmission by using the minimum resources. In this paper, we developed routing algorithm for cluster
based MANET and finds a path from source to destination using minimum cumulative degree path. Our
simulation results show that this routing algorithm provide efficient routing path with the increasing
number of nodes and uses multi-hop connectivity for intra-cluster to utilize minimum power for packet
transmission irrespective of number of nodes in the network.
Q-LEARNING BASED ROUTING PROTOCOL TO ENHANCE NETWORK LIFETIME IN WSNSIJCNCJournal
In resource constraint Wireless Sensor Networks (WSNs), enhancement of network lifetime has been one of the significantly challenging issues for the researchers. Researchers have been exploiting machine learning techniques, in particular reinforcement learning, to achieve efficient solutions in the domain of WSN. The objective of this paper is to apply Q-learning, a reinforcement learning technique, to enhance the lifetime of the network, by developing distributed routing protocols. Q-learning is an attractive choice for routing due to its low computational requirements and additional memory demands. To facilitate an agent running at each node to take an optimal action, the approach considers node’s residual energy, hop length to sink and transmission power. The parameters, residual energy and hop length, are used to calculate the Q-value, which in turn is used to decide the optimal next-hop for routing. The proposed protocols’ performance is evaluated through NS3 simulations, and compared with AODV protocol in terms of network lifetime, throughput and end-to-end delay.
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.
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.
Circular barcode design resistant to linear motion blur (preliminary slides)Naoki Shibata
It is hard to recognize markers from a moving camera, because of motion blur. Our circular barcode design allows fairly stable recognition even with linear motion blur. Each circular barcode can contain 9 bits of data. We developed an algorithm that recognizes barcodes at 30 frames/sec from 1080P video, utilizing GPGPU.
(Paper) An Endorsement Based Mobile Payment System for a Disaster AreaNaoki Shibata
Babatunde Ojetunde, Naoki Shibata, Juntao Gao, and Minoru Ito : An Endorsement Based Mobile Payment System for A Disaster Area, in Proc. of The 29th IEEE International Conference on Advanced Information Networking and Applications (AINA-2015) (29% acceptance rate), pp.482-489, Mar. 2015. DOI:10.1109/AINA.2015.225
A payment system in a disaster area is essential for people to buy necessities such as groceries, clothing, and medical supplies. However, existing payment systems require the needed communication infrastructures (like wired networks and cellular networks) to enable transactions, so that these systems cannot be relied on in disaster areas, where these communication infrastructures may be destroyed. In this paper, we propose a mobile payment system, adopting infrastructureless mobile adhoc networks (MANETs), which allow users to shop in disaster areas while providing secure transactions. Specifically, we propose an endorsement-based scheme to guarantee each transaction and a scheme to provide monitoring based on location information, and thus achieve transaction validity and reliability. Our mobile payment system can also prevent collusion between two parties and reset and recover attacks by any user. Security is ensured by using location-based mutual monitoring by nearby users, avoiding thereby double spending in the system.
BalloonNet: A Deploying Method for a Three-Dimensional Wireless Network Surro...Naoki Shibata
Aiming at fast establishment of a wireless network around a multi-level building in a disaster area, we propose an efficient method to determine the locations of network nodes in the air. Nodes are attached to balloons outside a building and deployed in the air so that the network can be accessed from anywhere in the building. In this paper, we introduce an original radio propagation model for predicting path loss from an outdoor position to a position inside a building. In order to address the three-dimensional deployment problem, the proposed method optimizes an objective function for satisfying two goals: (1) guarantee the coverage: the target space needs to be covered by over a certain percentage by wireless network nodes, (2) minimize the number of network nodes. For solving this problem, we propose an algorithm based on a genetic algorithm. To evaluate the proposed method, we compared our method with three benchmark methods, and the results show that the proposed method requires fewer nodes than other methods.
Congestion Alleviation Scheduling Technique for Car Drivers Based on Predicti...Naoki Shibata
In arranging efficient touring to various areas in urban areas, taking into account potential congestion is needed in order to schedule the order of these visits it is important to on the roads used and at the places to be visited. A number of scheduling methods have been proposed for finding (1) a noncongested route by sharing route information among users, or (2) a schedule to alleviate congestion at specific places based on the latest congestion information. However, these methods do not suffice since they do not deal with, simultaneously, congestion on road and at sites visited. In this paper, we propose a method of finding schedules for thousands of users by predicting, in advance, both types of congestion. Using the predicted results, the method adjusts each user’s provisional schedule by changing visiting order of places, and reducing their number in keeping with each user’s preferences. We have implemented the proposed method and evaluated it by simulations. The results showed it to achieve higher user satisfaction than existing methods.
(Paper) MTcast: Robust and Efficient P2P-based Video Delivery for Heterogeneo...Naoki Shibata
In this paper, we propose a new video delivery method called MTcast (Multiple Transcode based video multicast) which achieves efficient simultaneous video delivery to multiple users with different quality requirements by relying on user nodes to transcode and forward video to other user nodes. In MTcast, each user specifies a quality requirement for a video consisting of bitrate, picture size and frame rate based on the user’s environmental resource limitation. All users can receive video with the specified quality (or near this quality) along a single delivery tree. The main characteristics of MTcast are in its scalability, high user satisfaction degree in received video quality, short startup latency and robustness against node failure. Through simulations, we have confirmed that MTcast can achieve much higher user satisfaction degree and robustness against node failure than the layered multicast method.
An Endorsement Based Mobile Payment System for A Disaster AreaNaoki Shibata
Babatunde Ojetunde, Naoki Shibata, Juntao Gao, and Minoru Ito : An Endorsement Based Mobile Payment System for A Disaster Area, to appear in Proc. of The 29th IEEE International Conference on Advanced Information Networking and Applications (AINA-2015), Mar. 2015.
A payment system in a disaster area is essential for people to buy necessities such as groceries, clothing, and medical supplies. However, existing payment systems require the needed communication infrastructures (like wired networks and cellular networks) to enable transactions, so that these systems cannot be relied on in disaster areas, where these communication infrastructures may be destroyed. In this paper, we propose a mobile payment system, adopting infrastructureless mobile adhoc networks (MANETs), which allow users to shop in disaster areas while providing secure transactions. Specifically, we propose an endorsement-based scheme to guarantee each transaction and a scheme to provide monitoring based on location information, and thus achieve transaction validity and reliability. Our mobile payment system can also prevent collusion between two parties and reset and recover attacks by any user. Security is ensured by using location-based mutual monitoring by nearby users, avoiding thereby double spending in the system.
GreenSwirl: Combining Traffic Signal Control and Route Guidance for Reducing ...Naoki Shibata
Jiaxing Xu, Weihua Sun, Naoki Shibata and Minoru Ito : "GreenSwirl: Combining Traffic Signal Control and Route Guidance for Reducing Traffic Congestion," in Proc. of IEEE Vehicular Networking Conference 2014 (IEEE VNC 2014), pp. 179-186.
Serious traffic congestion is a major social problem in large cities. Inefficient setting of traffic signal cycles, especially, is one of the main causes of congestion. GreenWave is a method for controlling traffic signals which allows one-way traffic to pass through a series of intersections without being stopped by a red light. GreenWave was tested in several cities around the world, but the results were not satisfactory. Two of the problems with GreenWave are that it still stops the crossing traffic, and it forms congestion in the traffic turning into or out of the crossing streets. To solve these problems, we propose a method of controlling traffic signals, GreenSwirl, in combination with a route guidance method, GreenDrive. GreenSwirl controls traffic signals to enable a smooth flow of traffic through signals times to turn green in succession and through non-stop circular routes through the city. The GreenWave technology is extended thereby. We also use navigation systems to optimize the overall control of the city's traffic. We did a simulation using the traffic simulator SUMO and the road network of Manhattan Island in New York. We confirmed that our method shortens the average travel time by 10%-60%, even when not all cars on the road are equipped to use this system.
Task Scheduling Algorithm for Multicore Processor Systems with Turbo Boost an...Naoki Shibata
Yosuke Wakisaka, Naoki Shibata, Keiichi Yasumoto, Minoru Ito, and Junji Kitamichi : Task Scheduling Algorithm for Multicore Processor Systems with Turbo Boost and Hyper-Threading, In Proc. of The 2014 International Conference on Parallel and Distributed Processing Techniques and Applications(PDPTA'14), pp. 229-235
In this paper, we propose a task scheduling algorithm for multiprocessor systems with Turbo Boost and Hyper-Threading technologies. The proposed algorithm minimizes the total computation time taking account of dynamic changes of the processing speed by the two technologies, in addition to the network contention among the processors. We constructed a clock speed model with which the changes of processing speed with Turbo Boost and Hyper-threading can be estimated for various processor usage patterns. We then constructed a new scheduling algorithm that minimizes the total execution time of a task graph considering network contention and the two technologies. We evaluated the proposed algorithm by simulations and experiments with a multiprocessor system consisting of 4 PCs. In the experiment, the proposed algorithm produced a schedule that reduces the total execution time by 36% compared to conventional methods which are straightforward extensions of an existing method.
GPGPU-Assisted Subpixel Tracking Method for Fiducial MarkersNaoki Shibata
With an aim to realizing highly accurate position estimation, we propose in this paper a method for efficiently and accurately detecting the 3D positions and poses of traditional fiducial markers with black frames in high resolution images taken by ordinary web cameras. Our tracking method can be efficiently executed utilizing GPGPU computation, and in order to realize this, we devised a connected-component labeling method suitable for GPGPU execution. In order to improve accuracy, we devised a method for detecting 2D positions of the corners of markers in subpixel accuracy. We implemented our method in Java and OpenCL, and we confirmed that the proposed method provides better detection and measurement accuracy, and recognizing from high-resolution images is beneficial for improving accuracy. We also confirmed that our method is more than two times as fast as the existing method with CPU computation.
(Paper) BalloonNet: A Deploying Method for a Three-Dimensional Wireless Netwo...Naoki Shibata
Aiming at fast establishment of a wireless network around a multi-level building in a disaster area, we propose an efficient method to determine the locations of network nodes in the air. Nodes are attached to balloons outside a building and deployed in the air so that the network can be accessed from anywhere in the building. In this paper, we introduce an original radio propagation model for predicting path loss from an outdoor position to a position inside a building. In order to address the three-dimensional deployment problem, the proposed method optimizes an objective function for satisfying two goals: (1) guarantee the coverage: the target space needs to be covered by over a certain percentage by wireless network nodes, (2) minimize the number of network nodes. For solving this problem, we propose an algorithm based on a genetic algorithm. To evaluate the proposed method, we compared our method with three benchmark methods, and the results show that the proposed method requires fewer nodes than other methods.
(Paper) Emergency Medical Support System for Visualizing Locations and Vital ...Naoki Shibata
The triage tag is used in Mass Casualty Incident (MCI) to check the priority of patients treatments and conditions. However, it is difficult to grasp a change in the patient’s information since it is a paper tag. In this paper, we propose a system using the electronic triage tag (eTriage) that facilitates emergency medical technicians to grasp patients locations and conditions through visualization. This system provides the following three views of the patients information: (1) Inter-site view which shows on a map an overview of the latest status in multiple first-aid stations including the number of technicians and patients of each triage category; (2) Intra-site view which shows detailed status of each first-aid station including the location, triage category, and vital signs of each patient on a 3D map created based on the environment mapping technique; and (3) Individual view which shows vital information of patients on a tablet PC according to its orientation using the augmented reality technique. In this paper, we describe the design and implementation of the proposed system with some preliminary evaluation results.
(Paper) Parking Navigation for Alleviating Congestion in Multilevel Parking F...Naoki Shibata
Kenmotsu, M., Sun, W., Shibata, N., Yasumoto, K. and Ito, M. : "Parking Navigation for Alleviating Congestion in Multilevel Parking Facility," Proc. of 2012 IEEE 76th Vehicular Technology Conference (VTC2012-Fall), Sep.2012.
Abstract - Finding a vacant parking space in a large crowded parking facility takes long time. In this paper, we propose a navigation method that minimizes the parking time based on collected real-time positional information of cars. In the proposed method, a central server in the parking facility collects the information and estimates the occupancy of each parking zone. Then, the server broadcasts the occupancy data to the cars in the parking facility. Each car then computes a parking route with the shortest expected parking waiting time and shows it to the driver. We conducted simulation-based evaluations of the proposed method using a realistic model based on trace data taken from a real parking facility. We confirmed that the proposed method reduced parking waiting time by 20%–70% even with low system penetration.
Takashima, E.,Murata, Y., Shibata, N., Ito, M.: Self Adaptive Island GA, Proceedings of 2003 Congress on Evolutionary Computation (CEC 2003), Vol.2, pp.1072-1079, DOI:10.1109/CEC.2003.1299787
http://ito-lab.naist.jp/themes/pdffiles/031209.eiichi-t.cec2003.pdf
Exploration efficiency of GAs largely depends on parameter values. But, it is hard to manually adjust these values. T o cope with this problem, several adaptive GAs which automatically adjust parameters have been proposed. However , most of the existing adaptive GAs can adapt only a few parameters at the same time. Al-though several adaptive GAs can adapt multiple param-eters simultaneously , these algorithms require extremely large computation costs. In this paper , we propose Self Adaptive Island GA(SAIGA) which adapts four param-eter values simultaneously while finding a solution to a problem. SAIGA is a kind of island GA, and it adapts parameter values using a similar mechanism to meta-GA. Throughout our evaluation experiments, we con-firmed that our algorithm outperforms a simple GA us-ing De Jong's rational parameters, and has performance close to a simple GA using manually tuned parameter values.
(Paper) Efficient Evaluation Methods of Elementary Functions Suitable for SIM...Naoki Shibata
Naoki Shibata : Efficient Evaluation Methods of Elementary Functions Suitable for SIMD Computation, Journal of Computer Science on Research and Development, Proceedings of the International Supercomputing Conference ISC10., Volume 25, Numbers 1-2, pp. 25-32, DOI:10.1007/s00450-010-0108-2 (May. 2010).
http://ito-lab.naist.jp/~n-sibata/pdfs/isc10simd.pdf
http://freecode.com/projects/sleef
Data-parallel architectures like SIMD (Single Instruction Multiple Data) or SIMT (Single Instruction Multiple Thread) have been adopted in many recent CPU and GPU architectures. Although some SIMD and SIMT instruction sets include double-precision arithmetic and bitwise operations, there are no instructions dedicated to evaluating elementary functions like trigonometric functions in double precision. Thus, these functions have to be evaluated one by one using an FPU or using a software library. However, traditional algorithms for evaluating these elementary functions involve heavy use of conditional branches and/or table look-ups, which are not suitable for SIMD computation. In this paper, efficient methods are proposed for evaluating the sine, cosine, arc tangent, exponential and logarithmic functions in double precision without table look-ups, scattering from, or gathering into SIMD registers, or conditional branches. We implemented these methods using the Intel SSE2 instruction set to evaluate their accuracy and speed. The results showed that the average error was less than 0.67 ulp, and the maximum error was 6 ulps. The computation speed was faster than the FPUs on Intel Core 2 and Core i7 processors.
(Slides) A Decentralized Method for Maximizing k-coverage Lifetime in WSNsNaoki Shibata
Katsuma, R., Murata, Y., Shibata, N., Yasumoto, K., Ito, M.: "A Decentralized Method for Maximizing k-coverage Lifetime in WSNs," Proc. of The Sixth International Conference on Mobile Computing and Ubiquitous Networking (ICMU 2012), pp.16-23, May.23, 2012.
http://ito-lab.naist.jp/mediawiki/images/1/17/Icmu2012.pdf
In this paper, we propose a decentralized method for maximizing lifetime of data collection wireless sensor networks (WSNs) by making minimal number of nodes operate and putting other nodes in sleep. We divide a target field into multiple grids and make nodes in each grid locally achieve k-coverage. We can reduce energy consumption of WSN by minimizing the number of active nodes required for kcoverage. However, coverage degree is likely to go to excess beyond k near border between grids when deciding active nodes in each grid independently. To solve this problem, our method decides the minimal set of active nodes for adjoined grids at different times so that k-coverage of a grid is achieved taking into account the coverage in its neighboring grids. Through computer simulations, we confirmed that the proposed method achieved distribution of WSN processing with a small decrease of k-coverage lifetime compared to the centralized algorithm.
(Paper) Task scheduling algorithm for multicore processor system for minimiz...Naoki Shibata
Shohei Gotoda, Naoki Shibata and Minoru Ito : "Task scheduling algorithm for multicore processor system for minimizing recovery time in case of single node fault," Proceedings of IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2012), pp.260-267, DOI:10.1109/CCGrid.2012.23, May 15, 2012.
In this paper, we propose a task scheduling al-gorithm for a multicore processor system which reduces the
recovery time in case of a single fail-stop failure of a multicore
processor. Many of the recently developed processors have
multiple cores on a single die, so that one failure of a computing
node results in failure of many processors. In the case of a failure
of a multicore processor, all tasks which have been executed
on the failed multicore processor have to be recovered at once.
The proposed algorithm is based on an existing checkpointing
technique, and we assume that the state is saved when nodes
send results to the next node. If a series of computations that
depends on former results is executed on a single die, we need
to execute all parts of the series of computations again in
the case of failure of the processor. The proposed scheduling
algorithm tries not to concentrate tasks to processors on a die.
We designed our algorithm as a parallel algorithm that achieves
O(n) speedup where n is the number of processors. We evaluated
our method using simulations and experiments with four PCs.
We compared our method with existing scheduling method, and
in the simulation, the execution time including recovery time in
the case of a node failure is reduced by up to 50% while the
overhead in the case of no failure was a few percent in typical
scenarios.
(Slides) Task scheduling algorithm for multicore processor system for minimiz...Naoki Shibata
Shohei Gotoda, Naoki Shibata and Minoru Ito : "Task scheduling algorithm for multicore processor system for minimizing recovery time in case of single node fault," Proceedings of IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2012), pp.260-267, DOI:10.1109/CCGrid.2012.23, May 15, 2012.
In this paper, we propose a task scheduling al-gorithm for a multicore processor system which reduces the
recovery time in case of a single fail-stop failure of a multicore
processor. Many of the recently developed processors have
multiple cores on a single die, so that one failure of a computing
node results in failure of many processors. In the case of a failure
of a multicore processor, all tasks which have been executed
on the failed multicore processor have to be recovered at once.
The proposed algorithm is based on an existing checkpointing
technique, and we assume that the state is saved when nodes
send results to the next node. If a series of computations that
depends on former results is executed on a single die, we need
to execute all parts of the series of computations again in
the case of failure of the processor. The proposed scheduling
algorithm tries not to concentrate tasks to processors on a die.
We designed our algorithm as a parallel algorithm that achieves
O(n) speedup where n is the number of processors. We evaluated
our method using simulations and experiments with four PCs.
We compared our method with existing scheduling method, and
in the simulation, the execution time including recovery time in
the case of a node failure is reduced by up to 50% while the
overhead in the case of no failure was a few percent in typical
scenarios.
(Slides) A Technique for Information Sharing using Inter-Vehicle Communicatio...Naoki Shibata
Shinkawa, T., Terauchi, T., Kitani, T., Shibata, N., Yasumoto, K., Ito, M. and Higashino, T.: A Technique for Information Sharing using Inter-Vehicle Communication with Message Ferrying, International Workshop on Future Mobile and Ubiquitous Information Technologies (FMUIT'06).
http://mimi.naist.jp/~yasumoto/papers/FMUIT2006-shinkawa.pdf
In this paper, we propose a method to realize traffic information
sharing among cars using inter-vehicle communication.
When traffic information on a target area is retained
by ordinary cars near the area, the information may be lost
when the density of cars becomes low. In our method, we
use the message ferrying technique together with the neighboring
broadcast to mitigate this problem. We use buses
which travel through regular routes as ferries. We let buses
maintain the traffic information statistics in each area received
from its neighboring cars. We implemented the proposed
system, and conducted performance evaluation using
traffic simulator NETSTREAM. As a result, we have confirmed
that the proposed method can achieve better performance
than using only neighboring broadcast.
(Slides) A Personal Navigation System with a Schedule Planning Facility Based...Naoki Shibata
Shiraishi, T., Nagata, M., Shibata, N., Murata, Y., Yasumoto, K. and Ito, M.: A Personal Navigation System with a Schedule Planning Facility Based on Multiobjective Criteria, Proceedings of the 2nd International Conference on Mobile Computing and Ubiquitous Networking (ICMU2005), pp.104-109, (April 2005)
http://ito-lab.naist.jp/themes/pdffiles/icmu05-takayu-s.pdf
In our previous work, we have proposed a personal navigation
system called P-Tour, which facilitates tourists to compose
a schedule to visit multiple destinations taking into account
their preferences and time restrictions. In this paper,
we extend P-Tour in the following two ways: (1) allowing
users to optimize their tour schedules under multiple conflicting
criteria such as total expenses and satisfaction degrees;
and (2) navigating users to the next destination in more efficient
way. We have implemented the above extensions and
integrated them into P-Tour. Through some experiments, we
show the effectiveness of the proposed extensions.
(Slides) A Method for Distributed Computaion of Semi-Optimal Multicast Tree i...Naoki Shibata
Takashima, E., Murata, Y., Shibata, N., Yasumoto, K. and Ito, M.: A Method for Distributed Computaion of Semi-Optimal Multicast Tree in MANET, IEEE Wireless Communications and Networking Conference (WCNC 2007), pp. 2570-2575, DOI:10.1109/WCNC.2007.478 (March 2007).
http://ito-lab.naist.jp/themes/pdffiles/070314.eiichi-t.wcnc2007.pdf
In this paper, we propose a new method to construct
a semi-optimal QoS-aware multicast tree on MANET using
distributed computation of the tree based on Genetic Algorithm
(GA). This tree is sub-optimal for a given objective (e.g.,
communication stability and power consumption), and satisfies
given QoS constraints for bandwidth and delay. In order to
increase scalability, our proposed method first divides the whole
MANET to multiple clusters, and computes a tree for each
cluster and a tree connecting all clusters. Each tree is computed
by GA in some nodes selected in the corresponding cluster.
Through experiments using network simulator, we confirmed that
our method outperforms existing on-demand multicast routing
protocol in some useful objectives.
Essentials of Automations: Optimizing FME Workflows with ParametersSafe Software
Are you looking to streamline your workflows and boost your projects’ efficiency? Do you find yourself searching for ways to add flexibility and control over your FME workflows? If so, you’re in the right place.
Join us for an insightful dive into the world of FME parameters, a critical element in optimizing workflow efficiency. This webinar marks the beginning of our three-part “Essentials of Automation” series. This first webinar is designed to equip you with the knowledge and skills to utilize parameters effectively: enhancing the flexibility, maintainability, and user control of your FME projects.
Here’s what you’ll gain:
- Essentials of FME Parameters: Understand the pivotal role of parameters, including Reader/Writer, Transformer, User, and FME Flow categories. Discover how they are the key to unlocking automation and optimization within your workflows.
- Practical Applications in FME Form: Delve into key user parameter types including choice, connections, and file URLs. Allow users to control how a workflow runs, making your workflows more reusable. Learn to import values and deliver the best user experience for your workflows while enhancing accuracy.
- Optimization Strategies in FME Flow: Explore the creation and strategic deployment of parameters in FME Flow, including the use of deployment and geometry parameters, to maximize workflow efficiency.
- Pro Tips for Success: Gain insights on parameterizing connections and leveraging new features like Conditional Visibility for clarity and simplicity.
We’ll wrap up with a glimpse into future webinars, followed by a Q&A session to address your specific questions surrounding this topic.
Don’t miss this opportunity to elevate your FME expertise and drive your projects to new heights of efficiency.
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf91mobiles
91mobiles recently conducted a Smart TV Buyer Insights Survey in which we asked over 3,000 respondents about the TV they own, aspects they look at on a new TV, and their TV buying preferences.
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
A tale of scale & speed: How the US Navy is enabling software delivery from l...sonjaschweigert1
Rapid and secure feature delivery is a goal across every application team and every branch of the DoD. The Navy’s DevSecOps platform, Party Barge, has achieved:
- Reduction in onboarding time from 5 weeks to 1 day
- Improved developer experience and productivity through actionable findings and reduction of false positives
- Maintenance of superior security standards and inherent policy enforcement with Authorization to Operate (ATO)
Development teams can ship efficiently and ensure applications are cyber ready for Navy Authorizing Officials (AOs). In this webinar, Sigma Defense and Anchore will give attendees a look behind the scenes and demo secure pipeline automation and security artifacts that speed up application ATO and time to production.
We will cover:
- How to remove silos in DevSecOps
- How to build efficient development pipeline roles and component templates
- How to deliver security artifacts that matter for ATO’s (SBOMs, vulnerability reports, and policy evidence)
- How to streamline operations with automated policy checks on container images
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™UiPathCommunity
In questo evento online gratuito, organizzato dalla Community Italiana di UiPath, potrai esplorare le nuove funzionalità di Autopilot, il tool che integra l'Intelligenza Artificiale nei processi di sviluppo e utilizzo delle Automazioni.
📕 Vedremo insieme alcuni esempi dell'utilizzo di Autopilot in diversi tool della Suite UiPath:
Autopilot per Studio Web
Autopilot per Studio
Autopilot per Apps
Clipboard AI
GenAI applicata alla Document Understanding
👨🏫👨💻 Speakers:
Stefano Negro, UiPath MVPx3, RPA Tech Lead @ BSP Consultant
Flavio Martinelli, UiPath MVP 2023, Technical Account Manager @UiPath
Andrei Tasca, RPA Solutions Team Lead @NTT Data
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...James Anderson
Effective Application Security in Software Delivery lifecycle using Deployment Firewall and DBOM
The modern software delivery process (or the CI/CD process) includes many tools, distributed teams, open-source code, and cloud platforms. Constant focus on speed to release software to market, along with the traditional slow and manual security checks has caused gaps in continuous security as an important piece in the software supply chain. Today organizations feel more susceptible to external and internal cyber threats due to the vast attack surface in their applications supply chain and the lack of end-to-end governance and risk management.
The software team must secure its software delivery process to avoid vulnerability and security breaches. This needs to be achieved with existing tool chains and without extensive rework of the delivery processes. This talk will present strategies and techniques for providing visibility into the true risk of the existing vulnerabilities, preventing the introduction of security issues in the software, resolving vulnerabilities in production environments quickly, and capturing the deployment bill of materials (DBOM).
Speakers:
Bob Boule
Robert Boule is a technology enthusiast with PASSION for technology and making things work along with a knack for helping others understand how things work. He comes with around 20 years of solution engineering experience in application security, software continuous delivery, and SaaS platforms. He is known for his dynamic presentations in CI/CD and application security integrated in software delivery lifecycle.
Gopinath Rebala
Gopinath Rebala is the CTO of OpsMx, where he has overall responsibility for the machine learning and data processing architectures for Secure Software Delivery. Gopi also has a strong connection with our customers, leading design and architecture for strategic implementations. Gopi is a frequent speaker and well-known leader in continuous delivery and integrating security into software delivery.
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 3. In this session, we will cover desktop automation along with UI automation.
Topics covered:
UI automation Introduction,
UI automation Sample
Desktop automation flow
Pradeep Chinnala, Senior Consultant Automation Developer @WonderBotz and UiPath MVP
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Key Trends Shaping the Future of Infrastructure.pdfCheryl Hung
Keynote at DIGIT West Expo, Glasgow on 29 May 2024.
Cheryl Hung, ochery.com
Sr Director, Infrastructure Ecosystem, Arm.
The key trends across hardware, cloud and open-source; exploring how these areas are likely to mature and develop over the short and long-term, and then considering how organisations can position themselves to adapt and thrive.
Securing your Kubernetes cluster_ a step-by-step guide to success !KatiaHIMEUR1
Today, after several years of existence, an extremely active community and an ultra-dynamic ecosystem, Kubernetes has established itself as the de facto standard in container orchestration. Thanks to a wide range of managed services, it has never been so easy to set up a ready-to-use Kubernetes cluster.
However, this ease of use means that the subject of security in Kubernetes is often left for later, or even neglected. This exposes companies to significant risks.
In this talk, I'll show you step-by-step how to secure your Kubernetes cluster for greater peace of mind and reliability.
Securing your Kubernetes cluster_ a step-by-step guide to success !
(Paper) A Method for Overlay Network Latency Estimation from Previous Observation
1. A Method for Overlay Network Latency Estimation
from Previous Observation
Weihua Sun Naoki Shibata Keiichi Yasumoto Masaaki Mori
Nara Institute of Nara Institute of Nara Institute of Shiga University
Science and Technology Science and Technology Science and Technology 1-1-1 Banba, Hikone,
Ikoma, Japan 630–0192 Ikoma, Japan 630–0192 Ikoma, Japan 630–0192 Shiga, Japan 522–8522
sunweihua@is.naist.jp n-sibata@is.naist.jp yasumoto@is.naist.jp mori@biwako.shiga-u.ac.jp
Abstract—Estimation of the qualities of overlay links is useful disrupt measurements between other nodes. In general, the
for optimizing overlay networks on the Internet. Existing estima- network delay is considered to increase as the geographical
tion methods requires sending large quantities of probe packets distance or the number of routers in the route increases.
between two nodes, and the software for measurements have to
be executed at both of the end nodes. Accurate measurements However, due to the disproportionate data flow, large delay
require many probe packets to be sent, and other communication occurs at some specified routers. Also, there are detour of
can be disrupted by significantly increased network traffic. In physical communication links by geographical or political
this paper, we propose a link quality estimation method based reasons. Because of these reasons, link qualities are considered
on supervised learning from the previous observation of other to be attributed to the geographical positions of the two end
similar links. Our method does not need to exchange probe
packets, estimation can be quickly made to know qualities of nodes, rather than just the geographical distance between
many overlay links without wasting bandwidth and processing the nodes. We also need to consider the varying conditions
time on many nodes. We conducted evaluation of our method of congestion, and that the situation can suddenly change.
on PlanetLab, and our method showed better performance on However our observation tells that most of the links usually
path latency estimation than estimating results from geographical have relatively stable available bandwidths and delays. Since
distance between the two end nodes.
most people use the Internet in the daytime, there should be
constant periodical changes of link qualities. Thus, we assume
I. I NTRODUCTION
that we can estimate the degree of congestion of an overlay
In order to construct an efficient Peer-to-peer (P2P) overlay link from periodical observation of the link qualities in the
network, we need to know the link quality of overlay links, and past.
several methods for estimating link qualities such as available
We first discuss these assumptions by conducting exper-
bandwidth, packet-loss rate and latency between peers on the
iments on observing link qualities of PlanetLab nodes, and
Internet have been proposed. This kind of estimation methods
show that the assumptions stated above are probable. Then,
are also useful in client-server applications.
we explain our proposed method based on supervised learning
Existing estimation methods requires sending large quan-
for estimation of overlay link qualities from qualities observed
tities of probe packets between two nodes. Pathload[1] as-
in the past. Our method takes account of the geographical
sumes that a periodic packet stream shows an increasing
locations of end nodes to estimate the link qualities. Our
trend when the stream’s transmission rate is higher than the
experiments on PlanetLab showed that our method has good
available bandwidth, and it measures the available bandwidth
performance on path latency estimation. The estimation based
between two nodes. Abing [2] estimates the capacity of a path
on just geographical distance showed large error, especially
(bottleneck bandwidth) based on the observed the dispersion
when the distance is shorter than 2000 km. The proposed
experienced by two back-to-back packets. These methods
method achieved high estimation accuracy in that range. We
require measurement software to be executed at both of the
have shown a part of our results in a work-in-progress paper
end nodes. Since accurate measurements require many probe
[3], and we show detailed experimental results and discussion
packets to be sent, other communication can be disrupted by
in this paper.
significantly increased network traffic. Moreover, in order to
make more accurate measurement of link qualities, more probe In Sect. II, we provide an overview of related works, while
packets need to be sent into the network. If we could estimate in Sect. III we present a preliminary discussion on how
link qualities between each pair of nodes on the Internet. accurately we are able to estimate link qualities from those
Estimation of link qualities is useful for optimizing overlay previously observed. We propose a method for estimating link
networks on the Internet. However, the number of overlay qualities based on a supervised learning algorithm in IV and
links is the square of the number of peers, it is difficult to present the results of experiments on PlanetLab to demonstrate
estimate all the link qualities using the tools discussed above, the accuracy of the proposed method in Sect. V. Finally, our
since the packets for estimation between a pair of nodes can conclusions are given in Sect. VI.
2. II. R ELATED R ESEARCH AND C ONTRIBUTION proposed in [5] to estimate capacity and available bandwidth
Previously, in the field of wide area networks, many ap- without congesting the minimum capacity link in the path.
proaches were proposed to measure and estimate the delay Most of the existing bandwidth measurement methods and
and bandwidth between end nodes. Accurate estimation of the tools work by exchanging probe packets between sender and
available bandwidth is important for throughput optimization receiver nodes. Although these methods are useful for accurate
between end nodes, overlay network routing, peer-to-peer file bandwidth measurement, they generate traffic while measuring
distribution, traffic engineering, and capacity planning. In this bandwidth. SLoPS and TOPP, in particular, cause temporary
section, we discuss the measurement and prediction methods congestion of the minimum capacity link. Consequently, in a
with respect to the available path bandwidth between end large scale P2P network with millions of nodes, these methods
nodes. may cause serious deterioration in the network performance.
B. Bandwidth/Latency Prediction Method
A. Bandwidth Measurement Method
Various network traffic prediction models have been pro-
There are three different metrics for path bandwidth between
posed. In networks, similar traffic patterns with long time
end nodes: (1) capacity (maximum bandwidth), (2) available
intervals are said to be self-similar, while those patterns
bandwidth (maximum unused bandwidth), (3) TCP through-
with short time intervals are called multi-fractal. In [8], a
put/bulk transfer capacity (maximum achievable bandwidth).
method was proposed to predict network traffic at several time
The existing four measurement methodologies are:
steps in advance, based on past measured traffic information.
• VPS (Variable Packet Size probing) is a method to Moreover, the authors in [7] improved the method in [8], by
estimate link capacity by measuring the round-trip time; proposing a new ARIMA/GARCH model that predicts net-
that is, calculating the serialization delay of various sized work traffic with higher accuracy. In this model, self-similarity
packets sent from a sender node to a receiver node. and multi-fractals can be predicted by utilizing short-range and
• PPTD (Packet Pair/Train Dispersion) is a method for long-range dependencies. Through comparison experiments
measuring the capacity of the path between end nodes. with real network traffic, the authors showed that network
Letting a sender node continuously send uniform sized traffic can be predicted with reasonable accuracy.
packet pairs or trains to a receiver node, this approach These models aim to predict future traffic from previous
calculates the maximum link serialization delay in the detailed measurements. Moreover, the models can be used to
path to estimate the minimum link capacity (bottleneck) predict the available bandwidth and latency by separately mea-
by measuring the dispersion of the received packet times. suring the capacity of the path between the end nodes. Similar
• SLoPS (Self-Loading Periodic Streams) is a method to the above methods, the method in [9] accurately estimates
for measuring available bandwidth. While a sender node the latency of the path between end nodes based on traffic
continuously sends uniform sized packets to a receiver measurement. However, because detailed measurements are
node with transmission rate R, SLoPS observes the needed in advance, the models are not suitable for estimating
variation in delay for each packet at the destination node, bandwidth/latency at low cost owing to the additional traffic
and measures whether R is greater than A. By adjusting generated.
the transmission rate R, SLoPS estimates the available
bandwidth A. C. Contribution
• TOPP (Trains of Packet Pairs) measures capacity and The traffic prediction model makes use of the self-similarity
available bandwidth by transmitting data at a particular and multi-fractal properties of traffic. By applying these char-
transmission rate for a specified number of packet pairs. acteristics to the different nature of similar paths, link qualities
Unlike SLoPS, TOPP estimates the available bandwidth (including end to end delay, available bandwidth, and so on)
by increasing the transmission rate linearly and observing can be predicted using fewer a priori measurement results.
the arrival delay. In this paper, by considering the similarity of paths, we
Other tools that have been proposed and implemented are propose an overlay link quality prediction method, which
Pathchar, Clink, and Pchar for measuring link capacity, assumes that similar paths have similar characteristics. To the
Brpobe, Nettimer, Pathrate and Sprobe for measuring path best of the authors’ knowledge, there is no other prediction
capacity, Cprobe, Pathload, IGI, and pathChirp for measur- method that, like ours, does not require much bandwidth.
ing available bandwidth, and Treno, Cap, TTCP, NetPerf, Moreover, we have implemented the proposed method in
Iperf for measuring TCP throughput. As reported in [4], PlanetLab and evaluated the performance thereof.
Pathload and pathChirp showed better performance than
Abing, Spruce, and Iperf on a high-speed network testbed. III. P RELIMINARY E XPERIMENTS A ND O BSERVATION
Most of the above tools focus on measuring the average In this section, we first describe the results of two prelim-
available bandwidth, but do not consider bandwidth variation. inary experiments. In the first experiment, we observed the
Therefore, the authors in [6] proposed a method to measure fluctuations in link quality over time, while in the second, we
bandwidth variation. Moreover, with the goal of estimating investigated the relation between route (overlay link) similarity
the bandwidth without causing excessive traffic, a method was and the difference in link qualities. The amount of traffic on the
7. Fig. 3. Similarity Definition
Fig. 1. Observed fluctuation of latency (X axis = time )
RWKHU
(a) After 1 hour
Fig. 2. Observed fluctuation of available BW (X axis = time)
Internet changes continuously, influenced both by the day of
the week and the season. We observed the actual fluctuations
in link quality on PlanetLab. In the subsequent subsections, we
describe the configuration of the experiments, the definition of
route similarity, and the results of these experiments.
Observation of PlanetLab: We observed the fluctuations in
available bandwidth and latency between nodes in PlanetLab
over 7 days starting on 20th January 2011. We created 500 (b) After 6 days
random pairs among the nodes in PlanetLab and measured Fig. 4. Estimated latency by Proposed method, X axis = distance(Km)
the available bandwidth and latency using Pathload and ping
every hour. About 63000 valid data records were obtained. similarity between two overlay links based on geographical
Figure 1 shows a stacked bar graph of the observed latency distance. There are free databases from which we can find the
at each time divided by the latency observed at the beginning. geographical location of nodes from their IP addresses, and
The bottom series indicates the ratio of routes where the ob- thus it is easy to locate the geographical position of nodes on
served latency divided by the latency observed at the beginning the Internet. We also show the measurement results for link
was between 0.91 and 1.1. The second series indicates the similarity and the difference in link quality.
ratio of overlay links with latencies between 0.83 and 1.21 Route Similarity: As shown in Fig. 3, the route sim-
times. Figure 2 shows the results for bandwidth. From Fig. ilarity geo(v0 , v1 , v2 , v3 ) between two routes is defined as
1 it is clear that for 80% of the routes, the fluctuation in the minimum value between dist(v0 , v2 ) + dist(v1 , v3 ) and
latency was less than 10%, and this ratio did not change for dist(v0 , v3 ) + dist(v1 , v2 ), where dist(v0 , v1 ) denotes the
the whole week. Fig. 2 shows that for 70% of the routes, the geographical distance between v0 and v1 .
fluctuation in bandwidth was less than 10% for 20 hours from Measurements on PlanetLab: We created 500 random
the beginning of the experiment. It also shows that for half the pairs of nodes on PlanetLab, and investigated the relation
routes, bandwidth fluctuation was less than 10% for the week. between similarity as defined above and the observed latency.
We did not observe daily periodic fluctuations in bandwidth Figure 4(a) shows the relation between link similarity and
or latency. latency fluctuation one hour after the first measurement was
made, while Fig. 4(b) shows the results obtained six days after
A. Relation between Route Similarity and the Difference in the first measurement. We can see that these two graphs are
Link Quality almost identical, and that there is almost no change in the
It would be convenient if we could estimate the link quality fluctuation over time. We can also see that the amount of
of an unknown overlay link on which no link quality observa- fluctuation decreases with more similar routes. With the sum
tions have been made. To realize such a method, we first define of the distance less than 600 km, the fluctuation is within 50%
8. to 200% for 80% of the routes. Each peer sends the server a query to estimate the quality of
We also performed similar experiments on bandwidth, but the specified overlay links. When the server receives a query, it
did not observe any relation between route similarity and estimates the quality of the given links based on the proposed
fluctuation. This seems to be due to the fact that the available algorithm and sends the estimated result back to the peer.
bandwidth is usually limited by the bandwidth for the last The server carries out learning and estimation. In the
hop rather than that for the entire backbone. However, we are WKNN algorithm, the server performs learning using all
still investigating finding an appropriate similarity definition training samples stored in its memory. As time progresses,
for estimating the correct bandwidth. the number of training samples increases and more memory
space is required. To limit the required memory size, when the
IV. OVERLAY L INK Q UALITY E STIMATION M ETHOD number of training samples exceeds a predefined threshold, the
oldest samples are deleted from memory.
In this section, we propose an overlay link quality estimation
method based on the results of the preliminary experiments The size of a message that a peer exchanges with the server
in Sect. III. In the proposed method, (1) a centralized server (to upload the observed link quality, send a query for link
periodically collects, from various peers in the P2P network, quality estimation, or receive the estimation result) is at most
quality information of overlay links they have observed, and 200 bytes since it contains only an overlay link together with
(2) the quality of a given overlay link is estimated from the the associated quality.
information of previously observed overlay links based on the The server has a table that maps IP addresses to geographic
weighted k-nearest neighbor (W KN N ) algorithm, which is coordinates as explained in Sect. III-A.
one of the supervised learning techniques.
B. Learning algorithm
A. Preliminaries The proposed algorithm consists of two phases: (i) a learn-
1) Weighted k-nearest neighbor algorithm: The WKNN ing phase, and (ii) an estimation phase. We describe these
method uses training samples expressed as pairs of an object phases in detail below.
and a real number, and learns a function that maps an arbitrary 1) Learning phase: We assume that each peer participating
object to a real number. In our proposed method, the object in a target application communicates frequently with other
and real number correspond to an overlay link and latency, peers participating in the same application, e.g., to realize
respectively. video P2P streaming.
To use the WKNN algorithm, the following two functions In the proposed algorithm, each peer performs the following
must be given: (1) a function to calculate the distance between steps:
two objects; and (2) a function that assigns a weight to each • When the peer communicates with other peers, it mea-
object. sures the quality of the overlay links to those peers.
In the WKNN algorithm, learning is carried out using all • The peer periodically sends the quality of overlay links
training samples (the training set) stored in memory. When observed during the current period to the server. The
estimating a real number for an input object, WKNN selects message contains the IP addresses of both ends of each
the k samples in the training set geographically closest to the overlay link and the measured latency.
input object, and estimates a real number by calculating the
When the server receives the observed quality of an overlay
weighted average of the k samples with their weights.
link from a peer, it stores the data –that is, the IP addresses
2) Assumptions, estimation target, and algorithm outline:
of the end nodes of the overlay link and the latency, in its
We aim to apply the proposed method to estimate overlay
memory.
link quality in a P2P application such as video streaming. We
When the amount of data exceeds a predefined threshold,
assume that the P2P application consists of a central server
the server removes the oldest data from its memory.
and many peers (users). In the application, each peer observes
2) Estimation phase: When a peer wishes to know the
the quality of the overlay links directly connected to other
quality of an overlay link, it sends the server a query specifying
peers and periodically sends the observed information to the
the IP addresses of the end points of the link. When the server
server. In this study, we have designed the learning algorithm
receives the query, it estimates the quality of the specified link
as a centralized one, but it could easily be implemented as a
as follows:
distributed algorithm using, e.g., a distributed hash table.
The proposed algorithm is executed on the server and • The server selects the k closest training samples from the
estimates the quality of a given overlay link by applying the training set.
WKNN method to the previously observed quality information • It calculates the weight of each selected sample as ex-
collected by the server. As described in Sect. III-A, we plained in Sect. IV-B4.
could not find any correlation between link similarity and • It calculates the weighted average of the latency of the
the observed available bandwidth. Thus, we focus mainly on selected k samples.
overlay link latency as the quality estimation target in this • It sends the calculated result to the peer that originally
study. sent the query.
9. 3) Estimation example: Let us suppose that peer n0 has
sent the server a query regarding the overlay link between
itself and peer n1 . When the server receives the query, it selects
the k training samples closest to the overlay link between n0
and n1 based on the distance function defined in Sect. III-
A. Let us suppose that k = 2 and overlay links r1 and r2
have been selected. Then, the server calculates the weights of
r1 and r2 according to the method in Sect. IV-B4. Let the
weights for r1 and r2 be 1 and 2, respectively. Let us also
suppose that the previously observed latencies of r1 and r2
are 3 and 4, respectively. Finally, the server obtains the value
(1 × 3 + 2 × 4)/(3 + 4) = 1.57 as the weighted average and
sends this value as a reply to peer n0 . (a) k=1
4) Weight function: In Sect. III-A, we defined the similarity
between two overlay links observed at the same time. In
RWKHU
general, this similarity should be defined between two links
observed at different times. However, as explained in Sect.
III-A, the variation in latency with time is rather small. Thus,
we use the similarity function defined for two links observed
at the same time in the proposed algorithm.
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
According to the measurement results presented in Sect. III,
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000 000
more than 80% of overlay links experience a latency variation
between 0.71 and 1.41 times the initial measured latency.
Thus, we define the weight function as follows:
(b) k=3
0.3
W eight(us , ud , vs , vd )0.7 − · geo(us , ud , vs , vd ) (1)
5000
where (us , ud ) and (vs , vd ) are the geographic coordinates
of the target overlay link and the training sample, respectively.
V. E VALUATION
In this section, we evaluate the estimation accuracy of the
proposed method. According to the underlying principle of
the proposed method, the estimation accuracy depends on the
distance and time from the measured path. The greater the (c) k=5
difference in time or distance is, the worse is the estimation Fig. 5. Estimated bandwidth, X axis = time
accuracy. With respect to available bandwidth, we investigated
the relationship over time and estimation accuracy. With
respect to latency, we investigated the relationship over the
distance between paths and estimation accuracy. ϭϬϬϬϬ
Communication Delay (ms)
A. Evaluation of Available Bandwidth ϭϬϬϬ
As described above, despite the paths being similar, no
correlation with available bandwidth was observed. In this ϭϬϬ
experiment, using the k measured results of both cases of
one measurement per day and one measurement per hour on ϭϬ ǀĞƌĂŐĞ ĞůĂLJ
a certain path, we investigated the estimation accuracy when DĂdž ĞůĂLJ
varying k and the elapsed time from the last measurement. The DŝŶ ĞůĂLJ
ϭ
results are shown in Figs. 5(a)-5(c). According to these figures, ϬͲϭϬ ϯϭͲϭϬϬ ϭϬϬͲϯϭϲ ϯϭϲͲϭŬ ϭŬͲϯϭϲϮ ϯϭϲϮͲϭϬŬ ϭϬŬн
the observed estimation accuracy corresponds to the results of End to End Distance (km)
the preliminary experiments. However, the estimation accuracy Fig. 6. The average, maximum and minimum path delay
did not improve even when increasing k.
10. 2WKHU RWKHU
N N N N N N N N N N N
Fig. 7. Accuracy of Estimated delay based on path length (X axis = distance (a) k=1
(KM))
RWKHU
1) Estimation based on link distance: For comparison with
the proposed method, we used a delay estimation method
based on link distance. Figure 6 shows the relationship be-
tween link length and delay. According to this result, the
average delay of a path increases roughly in proportion to
the distance. However, the maximum and minimum delays do
not follow this trend. The delay calculated from the average
delay is 0.019 ms/km. The results of applying this value to
the delay estimation method are shown in Fig. 7. Obviously,
the estimation accuracy is low when the link distance is less
than 2000 km. (b) k=2
2) The proposed method: In this experiment, we inves-
tigated the accuracy of measuring path latency based on
RWKHU
the measured latency results of k different paths six days
previously. We investigated the estimation accuracy for a
number of distance functions by varying k. The results are
shown in Figs. 8(a) – 8(c).
According to these figures, accurate estimation was ob-
served. The estimation accuracy improved as k increased. In
particular, we confirmed that the estimation accuracy (0.71–
1.41 and 0.5–2.0) is very high for medium and short distances,
respectively.
VI. C ONCLUSION
(c) k=3
We proposed a learning-based overlay link quality estima- Fig. 8. Estimated latency by Proposed method, X axis = distance(Km)
tion method that uses the quality observed for other links in the
past. With respect to latency, by defining geographical similar- [4] Alok Shriram and Margaret Murray and Young Hyun and Nevil Brownlee
and Andre Broido and Marina Fomenkov and Kc Claffy : “Comparison of
ity between overlay links, the proposed method achieves good Public End-to-End Bandwidth Estimation Tools on High-Speed Links,”
estimation accuracy. With respect to bandwidth, we found in Proc. of of Passive and Active Measurement Workshop (PAM’05),
that there is no correlation between overlay links with close pp.306–320, 2005.
[5] Seong-ryong Kang and Xiliang Liu and Min Dai and and Dmitri Loguinov
geographical similarity. In the future, we intend devising a new and Dmitri Loguinov : “Packet-Pair Bandwidth Estimation: Stochastic
similarity metric to accurately estimate overlay link bandwidth Analysis Of a Single Congested Node,” in Proc. of 20th IEEE Interna-
taking into account domain type, connecting ISP, and so on. tional Conference on Network Protocols (ICNP’04), pp.316–325, 2004.
[6] Manish Jain and Constantinos Dovrolis : “End-to-end Estimation of
R EFERENCES the Available Bandwidth Variation Range,” in Proc. of the 2005 ACM
SIGMETRICS international conference on Measurement and modeling
[1] Jain, M. and Dovrolis, C. : “End-to-end available bandwidth: measure- of computer systems, pp.265-276, 2005.
ment methodology, dynamics, and relation with TCP throughput,” in [7] Bo Zhou and Dan He and Zhili Sun and Wee Hock Ng : “Network
IEEE/ACM Transactions on Networking, vol. 11, Issue 4, pp. 537–549, Traffic Modeling and Prediction with ARIMA/GARCH,” In 3rd inter-
2003. national working conference: performance modelling and evaluation of
[2] Jiri Navratil and R. Les Cottrell : “ABwE:A Practical Approach to Avail- heterogeneous networks (HET-NETs’05), 2005.
able Bandwidth Estimation,” in Proc. of Passive and Active Measurement [8] Aimin Sang and San-qi Li : “A Predictability Analysis of Network
Workshop (PAM’03), 2003. Traffic,” Proc. of IEEE INFOCOM 2000, pp.342–351, 2000.
[3] Weihua Sun, Naoki Shibata, Keiichi Yasumoto and Masaaki Mori : [9] Hariri, N. Hariri, B. and Shirmohammadi, S.: “A Distributed Measurement
“Estimation of Overlay Link Quality from Previously Observed Link Scheme for Internet Latency Estimation,” IEEE Trans. on Instrumentation
Qualities,” to appear in The 10th Annual IEEE Consumer Communi- and Measurement, 60 (5): pp.1594–1603, 2011
cations Networking Conference (CCNC’13), 2013.