SlideShare a Scribd company logo
Network-Assisted Delivery of Adaptive Video Streaming
Services through CDN,SDN,and MEC
Supervisors:
Univ.-Prof.DI Dr.Hermann Hellwagner
Univ.-Prof.DI Dr.Christian Timmerer
Reza Farahani
Klagenfurt am Wörthersee,Austria
22.08.2023
Reviewers:
Prof.Dr.Filip De Turck
Prof.Dr.Tobias Hoßfeld
Table of Contents
-Motivation
-Technical Background
-Research Questions
-Contributions
Introduction
1
4
2
Edge-and SDN-Assisted
Frameworks for HAS
3
SFC-Enabled Architecture
for HAS
Collaborative Edge-Assisted
Frameworks for HAS
5
Hybrid P2P-CDN
Architectures for HAS
06
Conclusions
6
-Conclusions
-Publications
2
Introduction
1
3
Motivation
2
3
4
5
6
1
4
● Video is dominating today’s Internet traffic
○ Video streaming includes 66% of the total video Internet traffic [1]
○ Video-on-Demand (VoD) and live streaming have become
significantly popular video streaming applications
○ Live streaming will increase 15-fold and reach 17% of Internet video
traffic [2]
[1] Sandvine, “The Global Internet Phenomena Report,” White Paper, 2023. https://www.sandvine.com/global-internet-phenomena-report-2023
[2] Cisco Visual Networking Index (VNI), Forecast and Trends, 2018– 2023. White Paper, 2018.
https://www.cisco.com/c/en/us/solutions/collateral/executive-perspectives/annual-internet-report/white-paper-c11-741490.pdf
HTTPAdaptive Video Streaming (HAS)
2
3
4
5
6
1
5
1
2
3
4
5 5
5
6
6
6 7
Encoder
Origin
Packager
CDNs
HTTP Res
HTTP Req
Reza Shokri Kalan, Reza Farahani, Emre Karsli, Christian Timmerer, and Hermann Hellwagner. Towards Low Latency Live Streaming: Challenges in a Real-world Deployment. 13th ACM MMSys, 2022.
Quality
Bandwidth
Time
Time
Network-Assisted Video Streaming (NAVS)
2
3
4
5
6
1
6
Network Assistance by HAS
Network Assistance for HAS
Network
Media Server
SFC
Modern NAVS Systems
2
3
4
5
6
1
7
SDN NFV
Hybrid Systems
NAVS Systems
Networking Paradigms
Content Delivery Networks
Emerging Protocols
Techniques
Computing Continuum Nodes
Edge
Cloud
Fog
CMAF
QUIC
LL-HAS
CMCD/SD
Transcoding
Multi Paradigms
Hybrid P2P-CDN
Caching Prefetching
CDN
P2P
Super-Resolution
Slicing
RQ1 How can SDNs/CDNs provide assistance for HAS clients in order to improve media
delivery services?
Research Questions
2
3
4
5
6
1
8
How can resources (i.e., computation, storage, bandwidth) provided by the
HAS clients be used to improve media delivery services?
RQ2
Research Questions
2
3
4
5
6
1
9
RQ3
RQ4
What is the utility of the proposed assistance and collaboration service?
How can the utility of the proposed NAVS frameworks be thoroughly evaluated,
both theoretically and practically?
Research Gaps
2
3
4
5
6
1
10
Contributions
2
3
4
5
6
1
11
Contributions
2
3
4
5
6
1
12
Edge and SDN-Assisted Framework for HAS
2
R. Farahani, et al. "ES-HAS: An Edge-and SDN-Assisted Framework for HTTP Adaptive Video Streaming", The 31st ACM
Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), 2021.
R. Farahani, et al. "CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming", IEEE 46th
Conference on Local Computer Networks (LCN), 2021.
13
Content Delivery Network (CDN)
14
3
4
5
6
1
2
Software Defined Networking (SDN)
15
3
4
5
6
1
2
Data Plane
Control Plane
https://opennetworking.org/sdn-definition/
Network Function Virtualization (NFV)
16
3
4
5
6
1
2
SABR Framework
3
4
5
6
1
2
17
Bhat, D., Rizk, A., Zink, M. and Steinmetz, R. Network assisted content distribution for adaptive bitrate video streaming. In Proceedings of the 8th ACM MMSys, 2017.
SABR: Network assisted content distribution for adaptive bitrate video streaming
Motivation
3
4
5
6
1
2
18
Motivation
3
4
5
6
1
2
18
Increasing the number of DASH clients ⇒ Increasing the number of exchanged
messages to/from the SDN controller
Multi-Access Edge Computing (MEC)
2
3
4
5
6
1
19
3
4
5
6
1
2
ES-HAS System
3
4
5
6
1
2
20
● ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming
○ Virtual Reverse Proxy (VRP) servers at the edge of an SDN-enablebd Network
Proposed System
3
4
5
6
1
2
21
Proposed System
3
4
5
6
1
2
21
The number of messages to/from the SDN controller
ES-HAS Architecture
3
4
5
6
1
2
22
ES-HAS Server/Segment Selection Policy
3
4
5
6
1
2
23
1. RAM
2. SOM
Fetching Time
Quality Deviation
Quality Bitrate
ES-HAS Testbed
3
4
5
6
1
2
24
● A cloud-based testbed, including 60 clients (Xen virtual machines) on CloudLab [1]
[1] https://www.cloudlab.us/
ES-HAS Results
3
4
5
6
1
2
25
CSDN System
3
4
5
6
1
2
26
● CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming
○ It equips the ES-HAS VRP with the transcoding capability
CSDN System
3
4
5
6
1
2
27
CSDN Server/Segment Selection Policy
3
4
5
6
1
2
28
Serving Time
Quality Deviation
1. When the requested quality level exist in the cache servers (Cache Hit)
○ find the cache server with minimum serving time
2. When the requested quality level is not available in any cache server (Cache Miss)
○ use replacement quality from a cache server with minimum fetch time
○ transcode the original quality from better quality level at the edge
○ fetch the original requested quality from the origin server
CSDN Testbed
3
4
5
6
1
2
29
● Extended ES-HAS testbed with 100 clients (Xen virtual machines) on CloudLab [1]
[1] https://www.cloudlab.us/
CSDN Results
3
4
5
6
1
2
30
CSDN Results
3
4
5
6
1
2
31
SFC-Enabled Architecture for HAS
3
R. Farahani, et al. "SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications", IEEE International Conference
on Communications (ICC), 2023.
32
Motivation
4
5
6
1
2
3
33
● OTT video
● Live video streaming
● Immersive multimedia
● Video Gaming
● Video analytics for security,
quality assurance, etc.
Increase in amount of video
generated and transported
Motivation
4
5
6
1
2
3
33
● OTT video
● Live video streaming
● Immersive multimedia
● Video Gaming
● Video analytics for security,
quality assurance, etc.
Increase in amount of video
generated and transported
Versatile QoE, QoS requirements
Resolution (4K, 8K)
Latency (LL,ULL)
Bitrate
Motivation
4
5
6
1
2
3
33
● OTT video
● Live video streaming
● Immersive multimedia
● Video Gaming
● Video analytics for security,
quality assurance, etc.
Increase in amount of video
generated and transported
Versatile QoE, QoS requirements
Resolution (4K, 8K)
Latency (LL,ULL)
Bitrate
Motivation
4
5
6
1
2
3
34
SDN
S
F
C
HAS
M
E
C
● How to leverage modern networking/computing paradigms to serve different MSs
requests with acceptable QoE and improved network utilization?
● How to design a network-assisted HAS scheme without client-side modification ?
Service Function Chaining (SFC)
4
5
6
1
2
3
35
VNF i VNF i+1 VNF n
VNF i VNF i+1 VNF n
SFC
Chains
Chain
1
Chain
m
…
…
…
Service Function Chaining (SFC)
4
5
6
1
2
3
35
VNF i VNF i+1 VNF n
VNF i VNF i+1 VNF n
SFC
Chains
Chain
1
Chain
m
…
…
…
Orchestration
Placement
Scheduling
SFC
Definition
VNF
Definition
SARENAArchitecture
4
5
6
1
2
3
36
Virtual Proxy Function
Virtual Cache Function
Virtual Transcoding Function
CDN Cache
Origin Cache
1
2
3
4
5
Multimedia
VNFs
SARENAArchitecture
4
5
6
1
2
3
37
3
1
2
5
Multimedia
SFCs
1
2
4
1
1
4
1 3
SARENA Optimization Model
4
5
6
1
2
3
38
● The Requests Scheduler run an MILP optimization model to respond:
○ Where is the optimal place for fetching the content quality level requested by each
client, while efficiently employing layers’ available resources and satisfying service
requirements (e.g., service deadlines)?
○ How can we use the functions/services provided in the EL and IL layers to form MS
function chains (SFCs)?
○ What is the optimal SFC for responding to the requested quality level with specific
service requirements?
Total MSs Serving Latency
Transmitting Time
Transcoding Time
SARENA Heuristic Solution
4
5
6
1
2
3
39
Virtual Scheduler Function
SARENATestbed
4
5
6
1
2
3
40
A cloud-based testbed, including 280 elements and real backbone topology (InternetMCI)
○ Xen virtual machines
○ 250 Dash player
○ Four Apache cache servers and an origin server
○ 19 backbone switches and 45 layer-2 links
○ Five edge server
○ Floodlight SDN controller
○ BOLA ABR algorithms
○ FFmpeg transcoders
○ LRU cache replacement policy
○ Zipf distribution is used for video and channel access popularity
SARENATestbed
4
5
6
1
2
3
41
0.089
320
480
720
1080
1080
0.262
0.791
2.4
4.2
Resolution (p) Bitrate (Mbps) Bitrate (Mbps)
Resolution (p)
20
VoDs,
300
sec.
duration,
4
sec.
segments
320
480
720
720
1080
1080
1080
0.128
0.32
0.78
1.4
2.4
3.3
3.9
5
live
ch,
300
sec.
duration,
2
sec.
segments
Evaluation Methods and Metrics
4
5
6
1
2
3
41
✔ Baseline systems:
◆ CDN-assisted (CDA)
◆ Non VNF-assisted (NVA)
◆ Non VTF-enabled (NTE)
◆ Non Reconfiguration-enabled (NRE)
✔ The performance of the aforementioned approaches is evaluated through
◆ ASB: Average Segment Bitrate
◆ AQS: Average Number of Quality Switches
◆ ANS: Average Number of Stalls
◆ ASD: Average Stall Duration
◆ APQ: Average Perceived QoE calculated by ITU-T P.1203 mode 0 [1]
◆ ASL: Overall time for serving
◆ NCV: Network Cost Value
◆ ETR: Edge/P2P Transcoding Ratio
◆ BTL: Backhaul Traffic Load
[1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
SARENA Results
4
5
6
1
2
3
42
ASB: Average Segment Bitrate
AQS: Average Number of Quality
Switches
ANS: Average Number of Stalls
ASD: Average Stall Duration
APQ: Average Perceived QoE
calculated by ITU-T P.1203 mode 0 [1]
ASL: Average Serving Latency
[1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
SARENA Results
4
5
6
1
2
3
43
NCV: Network Cost Value
ETR: Edge Transcoding Ratio
BTL: Backhaul Traffic Load
Collaborative Edge-Assisted Frameworks for HAS
4
R. Farahani, et al., "LEADER: A Collaborative Edge- and SDN-Assisted Framework for HTTP Adaptive Video
Streaming". IEEE International Conference on Communications (ICC), 2022.
R. Farahani, et al., "ARARAT: A Collaborative Edge-Assisted Framework for HTTP Adaptive Video Streaming", IEEE
Transactions on Network and Service Management (TNSM), 2022.
5
6
1
2
3
4
45
Motivation
✔ Establish a collaboration between edge servers to use their potential idle
resources for serving HAS clients.
M
E
C
SDN
N
F
V
H
A
S
5
6
1
2
3
4
46
Proposed Collaborative Systems
5
6
1
2
3
4
47
LEADER/ARARATARCHITECTURE
✔ MEC Servers:
◆ Local Edge Server (LES)
◆ Neighboring Edge Server (NES)
✔ Virtualized Edge Functions:
◆ Partial Cache (PC)
◆ Video Transcoder (Tran)
Edge Layer
5
6
1
2
3
4
47
LEADER/ARARATARCHITECTURE
5
6
1
2
3
4
47
LEADER/ARARATARCHITECTURE
cache_map
Requests, edge_map, comp_map
LEADER and ARARATAction Tree
4
5
6
1
2
3
48
5
6
1
2
3
4
LEADER Action Tree ARARAT Action Tree
LEADER/ARARAT Optimization Models
4
5
6
1
2
3
49
● The SDN controller run an MILP optimization model to respond:
○ Where is the optimal place (i.e., LES, NESs, CSs, or the origin server) in terms of the
following items for fetching each client’s requested content quality level from?
■ minimum serving time (LEADER)
■ minimum serving time and minimum network cost (ARARAT)
○ What is the optimal approach for responding to the requested quality level (i.e., fetch
or transcode)?
Serving Latency
5
6
1
2
3
4
Network Cost
LEADER ARARAT
ARARAT Coarse-Grained (CG) Heuristic
4
5
6
1
2
3
49
5
6
1
2
3
4
COM → LOM
ARARAT Fine-Grained I (FG I) Heuristic
4
5
6
1
2
3
50
5
6
1
2
3
4
LOM → EFG I
ARARAT Fine-Grained I (FG I) Heuristic
4
5
6
1
2
3
50
5
6
1
2
3
4
LOM → EFG I
Network bandwidth allocation?
ARARAT Fine-Grained II (FG II) Heuristic
4
5
6
1
2
3
51
5
6
1
2
3
4
EFG I → EFG II
ARARAT Fine-Grained II (FG II) Heuristic
4
5
6
1
2
3
52
5
6
1
2
3
4
The bandwidth allocation is modeled as a “Fairness LP Optimization Model”
ARARATTestbed
1
53
● A cloud-based testbed, including 301 elements (Xen virtual machines) and real backbone topology
(Geant and Abilene)
4
5
6
1
2
3
5
6
1
2
3
4
1
54
4
5
6
1
2
3
5
6
1
2
3
4
Evaluation Methods
✔ SABR:
◆ Non edge-enabled system
✔ ES-HAS
◆ Non edge-collaborative and transcoding-enabled system
◆ Each edge runs an MILP model on the collected client requests to serve them via one of actions
1, 7, or 9
✔ CSDN
◆ Non-collaborative approach
◆ Each edge server runs an MILP model for the collected client requests and serves them
separately via one of the actions 1, 2, 7, 8 or 9
✔ NECOL
◆ The Non Edge Collaborative (NECOL) system does not support an edge collaboration.
◆ Each NECOL edge server executes a simplified version of the proposed FG I heuristic for
◆ each client request to serve it through one of the actions 1, 2, 7, 8 or 9
✔ DECOL
◆ Default Edge Collaborative (DECOL)
◆ Run the proposed FG I heuristic
1
55
4
5
6
1
2
3
5
6
1
2
3
4
LEADER Results
ASB: Average Segment Bitrate
AQS: Average Number of Quality Switches
ANS: Average Number of Stalls
ASD: Average Stall Duration
APQ: Average Perceived QoE calculated by
ITU-T P.1203 mode 0 [1]
CHR: Cache Hit Ratio
ETR: Edge Transcoding Ratio
BTL: Backhaul Traffic Load
[1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
1
56
4
5
6
1
2
3
5
6
1
2
3
4
ARARAT Results
ASB: Average Segment Bitrate
AQS: Average Number of Quality
Switches
ANS: Average Number of Stalls
ASD: Average Stall Duration
APQ: Average Perceived QoE
calculated by ITU-T P.1203 mode 0 [1]
[1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
1
57
4
5
6
1
2
3
5
6
1
2
3
4
ARARAT Results
CHR: Cache Hit Ratio
ETR: Edge Transcoding Ratio
BTL: Backhaul Traffic Load
ANU: Average Network Utilization
ASL: Average Serving Time
NCV: Network Cost Value
ANC: Average Number of Communicated
messages from/to the SDN controller
Hybrid P2P-CDN Architectures for HAS
5
R. Farahani, et al., "Hybrid P2P-CDN Architecture for Live Video Streaming: An Online Learning Approach”. IEEE Global
Communications Conference (GLOBECOM), 2022.
R. Farahani, et al., "RICHTER: Hybrid P2P- CDN Architecture for Low Latency Live Video Streaming”. ACM Mile-High Video
Conference (MHV), 2022.
R. Farahani, et al., "ALIVE: A Latency- and Cost-Aware Hybrid P2P-CDN Framework for Live Video Streaming", submitted to
IEEE Transactions on Network and Service Management (TNSM), 2023.
Peer-to-Peer Network (P2P)
59
6
1
2
3
4
5
Tracker
Motivation
6
1
2
3
4
5
60
✔ Employ all potential resources (storage, bandwidth, computation) of the P2P network
✔ Utilize P2P and CDN resources efficiently
✔ Satisfy HAS client requests with acceptable QoE and improved latency
CDN P2P
61
Proposed Collaborative Systems
6
1
2
3
4
5
ALIVE Architecture
6
1
2
3
4
5
62
✔ RICHTER does not include the PSR function.
RICHTER and ALIVE Action Tree
63
RICHTER Action Tree ALIVE Action Tree
6
1
2
3
4
5
RICHTER/ALIVE Optimization Models
4
5
6
1
2
3
64
● The VTS server must respond:
○ Where is the optimal place (i.e., adjacent peers, VTS, CDN servers, or origin server) in
terms of the following items for fetching each client’s requested content quality level
from?
■ minimum serving time (RICHTER)
■ minimum serving time and minimum network cost (ALIVE)
○ What is the optimal approach for responding to the requested quality level (i.e., fetch
,transcode, or upscale)?
Serving Latency
5
6
1
2
3
4 Network Cost
RICHTER ALIVE
6
1
2
3
4
5
RICHTER Online Learning (OL) Approach
4
5
6
1
2
3
65
● Leverage new modules, classification technique to introduce an OL heuristic approach
● Self Organizing Map (SOM) is adopted as the request management solution in the OL agent:
○ popular technique for unsupervised classification problems
○ can be applied to solve NP-hard problems
○ does not require a prepared dataset for supervised model training
● Alive runs a simplified version that is based on the Greedy approach
5
6
1
2
3
4
6
1
2
3
4
5
Node
Action
Req#
Violation
ALIVE Greedy-Based Heuristic Approach
4
5
6
1
2
3
65
5
6
1
2
3
4
6
1
2
3
4
5
ALIVE Testbed
4
5
6
1
2
3
66
5
6
1
2
3
4
6
1
2
3
4
5
● A cloud-based testbed, including 375 elements (Xen virtual machines) and real backbone
topology (InternetMCI)
● Apple M1, Xiaomi Mi11, and iPhone 11
67
Evaluation Methods
✔ NOH:
◆ Non Hybrid system like traditional CDN based methods
✔ SEH:
◆ Simple Edge-enabled Hybrid
◆ It employs a simple VTS server without caching and transcoding capabilities
✔ NTH
◆ Non Transcoding-enabled Hybrid
◆ It has a VTS server with only caching capability
✔ ECT
◆ Edge Caching/Transcoding Hybrid
◆ It does not include transcoding and super-resolution at the peer side
✔ NSH
◆ Non SR-enabled Hybrid (RICHTER using Greedy apprach)
◆ There is no super-resolution feature on the peer side
4
5
6
1
2
3
5
6
1
2
3
4
6
1
2
3
4
5
68
P2PTR/SR Results
4
5
6
1
2
3
5
6
1
2
3
4
6
1
2
3
4
5
69
RICHTER Results
4
5
6
1
2
3
5
6
1
2
3
4
6
1
2
3
4
5
ASB: Average Segment Bitrate
AQS: Average Number of Quality Switches
ANS: Average Number of Stalls
ASD: Average Stall Duration
APQ: Average Perceived QoE calculated by
ITU-T P.1203 mode 0 [1]
ASL: Average Serving Time
CHR: Cache Hit Ratio
ETR: Edge Transcoding Ratio
BTL: Backhaul Traffic Load
[1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
70
ALIVE Results
4
5
6
1
2
3
5
6
1
2
3
4
6
1
2
3
4
5
ASB: Average Segment Bitrate
AQS: Average Number of Quality Switches
ANS: Average Number of Stalls
ASD: Average Stall Duration
ASL: Average Serving Time
APQ: Average Perceived QoE calculated by
ITU-T P.1203 mode 0 [1]
[1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
71
ALIVE Results
4
5
6
1
2
3
5
6
1
2
3
4
6
1
2
3
4
5
CHR: Cache Hit Ratio
ETR: Edge Transcoding Ratio
PTSR: Peer SR and TR Ratio
BTL: Backhaul Traffic Load
EEC: Edge Energy Consumption for running
ETR
NCV: Network Cost Value
Conclusions
6
Conclusions
How can SDNs/CDNs provide assistance for HAS clients in
order to improve media delivery services?
RQ1
1
2
3
4
5
6 73
● ES-HAS and CSDN frameworks
○ Introduce Virtual Reverse Proxy function to act as a gateway between HAS
clients and the network
○ Design new server/segment selection policies
● SARENA framework
○ Design VNFs that can be chained under an SDN controller’s coordination to
establish different types of video streaming services
● LEADER and ARARAT frameworks
○ Establish a collaboration between edge servers under an SDN controller’s
coordination
○ Propose Action Tree including all possible actions to serve requests
○ Propose fair bandwidth allocation startegies
Conclusions
How can resources (i.e., computation, storage, bandwidth)
provided by the HAS clients be used to improve media delivery
services?
RQ2
1
2
3
4
5
6 74
● RICHTER and ALIVE frameworks
○ Hybrid P2P-CDN NAVS systems for HAS clients in live streaming
applications
○ Employing idle computational resources and available bandwidth of HAS
clients (i.e., peers) to offer distributed video processing services, such as video
transcoding and video super- resolution.
○ Propose Action Tree including all possible actions to serve requests
○ Propose heuristic algorithms to play decision-maker roles in large-scale
practical scenarios.
Conclusions
What is the utility of the proposed assistance and
collaboration service?
RQ3
1
2
3
4
5
6 75
● User QoE metrics (application QoS)
○ quality bitrate, number of quality switches, number of stalls, stalling duration,
serving times, VMAF values, standardized perceived quality.
● Network utilization metrics
○ cache hit ratio, transcoding ratio at the edge, transcoding ratio at the P2P
network, super-resolution ratio at the P2P network, computational cost,
backhaul bandwidth cost, number of communicated messages to/from the
SDN controller.
● Algorithm performance metrics
○ execution times and objective function values
Conclusions
RQ4
1
2
3
4
5
6 76
How can the utility of the proposed NAVS frameworks be
thoroughly evaluated, both theoretically and practically?
● Desine cloud-based testbeds to run realistic network topologies for all
proposed frameworks
○ Use tens/hundreds of elements, each of which runs Linux-based operating
systems inside Xen virtual machines.
○ Use two different ABR algorithm
○ Employ bitrate ladders of real video datasets
○ Use OpenFlow backbone switches and Floodlight SDN controller
○ Use realistic network traces, tools, and assumptions
○ Compare results with state-of-the-art and baseline approaches
First Author Publications
77
1. R. Farahani, E. Cetinkaya, C. Timmerer, M. Shojafar, M. Ghanbari, H. Hellwagner. ALIVE: A Latency- and Cost-Aware Hybrid P2P-CDN
Framework for Live Video Streaming. Submitted to IEEE Transactions on Network and Service Management (TNSM), 2023.
2. R. Farahani, C. Timmerer, H. Hellwagner. Towards Low-Latency and Energy-Efficient Hybrid P2P-CDN Live Video Streaming.
Submitted to IEEE COMSOC MMTC Communication-Frontiers, 2023.
3. R. Farahani, M. Shojafar, C. Timmerer, F. Tashtarian, M. Ghanbari, H. Hellwagner. ARARAT: A Collaborative Edge-Assisted Framework
for HTTP Adaptive Video Streaming. IEEE Transactions on Network and Service Management (TNSM), 2022.
4. R. Farahani, A. Bentaleb, C. Timmerer, M. Shojafar, R. Prodan, H. Hellwagner. SARENA: SFC-Enabled Architecture for Adaptive Video
Streaming Applications. IEEE International Conference on Communications (ICC), 2022.
5. R. Farahani, A. Bentaleb, E. Cetinkaya, C. Timmerer, R. Zimmermann, H. Hellwagner. Hybrid P2P-CDN Architecture for Live Video
Streaming: An Online Learning Approach. IEEE Global Communications Conference (GLOBECOM), 2022.
6. R. Farahani, F. Tashtarian, C. Timmerer, M. Ghanbari, H. Hellwagner. LEADER: A Collaborative Edge- and SDN-Assisted Framework for
HTTP Adaptive Video. IEEE International Conference on Communications (ICC), 2022.
7. R. Farahani, F. Tashtarian, H. Amirpour, C. Timmerer, M. Ghanbari, H. Hellwagner. CSDN: CDN-Aware QoE Optimization in SDN-Assisted
HTTP Adaptive Video Streaming. 46th IEEE Conference on Local Computer Networks (LCN), 2021.
8. R. Farahani, F. Tashtarian, A. Erfanian, C. Timmerer, M. Ghanbari, H. Hellwagner. ES-HAS: an edge- and SDN-assisted framework for
HTTP adaptive video streaming. 31st ACM Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV),
2021.
9. R. Farahani. CDN and SDN Support and Player Interaction for HTTP Adaptive Video Streaming. 12th ACM Multimedia Systems
Conference (MMSys), 2021.
10. R. Farahani, A. Bentaleb, M. Shojafar, H. Hellwagner. CP-Steering: CDN- and Protocol-Aware Content Steering Solution for HTTP
Adaptive Video Streaming. ACM Mile High Video (MHV), 2023.
11. R. Farahani, H. Amirpour, F. Tashtarian, A.Bentaleb, C. Timmerer, H. Hellwagner, and R. Zimmermann. RICHTER: Hybrid P2P-CDN
Architecture for Low Latency Live Video Streaming. ACM Mile-High Video (MHV), 2022.
Co-authored Publications
78
1. V. V Menon, R. Farahani, P. T Rajendran, H. Hellwagner, M. Ghanbari, C. Timmerer. Reduced Reference Transcoding Quality
Prediction for Video Streaming Applications. ACM Mile High Video (MHV), 2023.
2. V. V Menon, P. T Rajendran, R. Farahani, K. Schöffmann, C. Timmerer. Video Quality Assessment with Texture Information Fusion
for Streaming Applications. Submitted to the IEEE International Conference on Visual Communications and Image Processing (VCIP),
2023.
3. V. V Menon, R. Farahani, P. T Rajendran, S. Afzal, K. Schöffmann, C. Timmerer. Energy-Efficient Multi-Codec Bitrate-Ladder
Estimation for Adaptive Video Streaming. Submitted to the IEEE International Conference on Visual Communications and Image
Processing (VCIP), 2023.
4. S. Chellappa, R. Farahani, R. Bartos, H. Hellwagner. Context-Aware HTTP Adaptive Video Streaming Utilizing QUIC’s Stream Priority.
ACM Mile High Video (MHV), 2023.
5. A. Bentaleb, R. Farahani, F. Tashtarian, H. Hellwagner, R.Zimmermann. Which CDN to Download From? A Client and Server
Strategies. ACM Mile High Video (MHV), 2023.
6. R. Shokri Kalan, R. Farahani, E. Karsli, C. Timmerer, H. Hellwagner. Towards Low Latency Live Streaming: Challenges in
Real-World Deployment. The 13th ACM Multimedia Systems Conference (MMSys), 2022.
7. F. Tashtarian, A. Bentaleb, R. Farahani, M. Nguyen, C. Timmerer, H.Hellwagner, R. Zimmermann. A Distributed Delivery Architecture
for User Generated Content Live Streaming over HTTP. IEEE 46th Conference on Local Computer Networks (LCN), 2021.
8. A. Erfanian, F. Tashtarian, R. Farahani, C. Timmerer, H. Hellwagner. On Optimizing Resource Utilization in AVC-based Real-time
Video Streaming. The 6th IEEE Conference on Network Softwarization (NetSoft), 2020.
Thank you
Future Directions
Traffic Encryption
Immersive Streaming
Emerging Protocols
Grean Streaming
RICHTER Online Learning (OL) Approach
4
5
6
1
2
3
65
● Leverage new modules, classification technique to introduce an OL heuristic approach
● Self Organizing Map (SOM) is adopted as the request management solution in the OL agent:
○ popular technique for unsupervised classification problems
○ can be applied to solve NP-hard problems
○ does not require a prepared dataset for supervised model training
● Alive runs a simplified version that is based on the Greedy approach
5
6
1
2
3
4
6
1
2
3
4
5
Node
Action
Req#
Violation
Statistics Calculation
IM= (New Value - Old Value) / Old Value
ES-HAS Results
3
4
5
6
1
2
94
ES-HAS Results
3
4
5
6
1
2
ES-HAS Results
3
4
5
6
1
2
● We analyze the Impact of different parameters on ES-HAS MILP model behavior by:
○ ACS : the average usage percentage of cache servers with the shortest fetch time
○ AMD: the average (for different accepted max-deviation value) of the maximum
deviation between requested quality and forwarded quality
○ AQB: the average of the video quality bitrate for all received segments in Mbps
Problem Formulation
Central MILP Optimization Model
Constraints & Objective Function
✓ Resource Map
✓ Requests
✓ Videos Information
✓ Computational Cost
Optimal action for each request
Fine-Grained II (FG II)-- Bandwidth Allocation Strategy
BwAllocation request
Minimum fairness value among
all fairness coefficient.
✔ The bandwidth allocation is modeled as a “Fairness LP Optimization Model”
The fairness coefficient to the shared link(a, b)
in the route between i and j.
The allocated bandwidth to the shared link(a, b)
in the route between i and j.
98
Bandwidth Allocation Strategy
Evaluation Results-- Scenario I
✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG
approaches in terms of:
◆ ETV: Execution Time Values for the different ARARAT schemes.
◆ NOV: Normalized Objective Value for the ARARAT schemes.
Evaluation Results-- Scenario I
✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG
approaches in terms of:
◆ ETV: Execution Time Values for the different ARARAT schemes.
◆ NOV: Normalized Objective Value for the ARARAT schemes.
Evaluation Results-- Scenario I
✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG
approaches in terms of:
◆ ETV: Execution Time Values for the different ARARAT schemes.
◆ NOV: Normalized Objective Value for the ARARAT schemes.
Evaluation Results-- Scenario I
✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG
approaches in terms of:
◆ ETV: Execution Time Values for the different ARARAT schemes.
◆ NOV: Normalized Objective Value for the ARARAT schemes.
ALIVE Results

More Related Content

Similar to Network-Assisted Delivery of Adaptive Video Streaming Services through CDN, SDN, and MEC

Video Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive StreamingVideo Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive Streaming
Alpen-Adria-Universität
 
Research@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdfResearch@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdf
Vignesh V Menon
 
IEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdfIEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdf
Reza Farahani
 
Collaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
Collaborative Edge-Assisted Systems for HTTP Adaptive Video StreamingCollaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
Collaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
Alpen-Adria-Universität
 
USuurey_Presentation__CollaborativeHASSystems.pdf
USuurey_Presentation__CollaborativeHASSystems.pdfUSuurey_Presentation__CollaborativeHASSystems.pdf
USuurey_Presentation__CollaborativeHASSystems.pdf
Reza Farahani
 
HTTP Adaptive Streaming – Where Is It Heading?
HTTP Adaptive Streaming – Where Is It Heading?HTTP Adaptive Streaming – Where Is It Heading?
HTTP Adaptive Streaming – Where Is It Heading?
Alpen-Adria-Universität
 
Doctoral Symposium presentation.pdf
Doctoral Symposium presentation.pdfDoctoral Symposium presentation.pdf
Doctoral Symposium presentation.pdf
Vignesh V Menon
 
Optimizing QoE and Latency of Live Video Streaming Using Edge Computing a...
Optimizing  QoE and Latency of  Live Video Streaming Using  Edge Computing  a...Optimizing  QoE and Latency of  Live Video Streaming Using  Edge Computing  a...
Optimizing QoE and Latency of Live Video Streaming Using Edge Computing a...
Alpen-Adria-Universität
 
QoS Constrained H.264/SVC video streaming over Multicast Ad Hoc Networks
QoS Constrained H.264/SVC video streaming over Multicast Ad Hoc NetworksQoS Constrained H.264/SVC video streaming over Multicast Ad Hoc Networks
QoS Constrained H.264/SVC video streaming over Multicast Ad Hoc Networks
IJERA Editor
 
WebRTC overview
WebRTC overviewWebRTC overview
WebRTC overview
Rouyun Pan
 
Immersive Video Delivery: From Omnidirectional Video to Holography
Immersive Video Delivery: From Omnidirectional Video to HolographyImmersive Video Delivery: From Omnidirectional Video to Holography
Immersive Video Delivery: From Omnidirectional Video to Holography
Alpen-Adria-Universität
 
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual RealityFixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Wen-Chih Lo
 
Digital Media Production - Future Internet
Digital Media Production - Future InternetDigital Media Production - Future Internet
Digital Media Production - Future InternetMaarten Verwaest
 
6NEAT project and IP..
6NEAT project and IP..6NEAT project and IP..
6NEAT project and IP..Videoguy
 
Monitoring whole mpeg transport stream
Monitoring whole mpeg transport streamMonitoring whole mpeg transport stream
Monitoring whole mpeg transport streamVolicon
 
QoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
QoE- and Energy-aware Content Consumption for HTTP Adaptive StreamingQoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
QoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
DanieleLorenzi6
 
Multi-Criteria Optimization of Content Delivery within the Future Media Internet
Multi-Criteria Optimization of Content Delivery within the Future Media InternetMulti-Criteria Optimization of Content Delivery within the Future Media Internet
Multi-Criteria Optimization of Content Delivery within the Future Media Internet
jbruneauqueyreix
 
Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...Videoguy
 
Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...Videoguy
 

Similar to Network-Assisted Delivery of Adaptive Video Streaming Services through CDN, SDN, and MEC (20)

Video Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive StreamingVideo Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive Streaming
 
Research@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdfResearch@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdf
 
IEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdfIEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdf
 
Collaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
Collaborative Edge-Assisted Systems for HTTP Adaptive Video StreamingCollaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
Collaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
 
USuurey_Presentation__CollaborativeHASSystems.pdf
USuurey_Presentation__CollaborativeHASSystems.pdfUSuurey_Presentation__CollaborativeHASSystems.pdf
USuurey_Presentation__CollaborativeHASSystems.pdf
 
HTTP Adaptive Streaming – Where Is It Heading?
HTTP Adaptive Streaming – Where Is It Heading?HTTP Adaptive Streaming – Where Is It Heading?
HTTP Adaptive Streaming – Where Is It Heading?
 
Doctoral Symposium presentation.pdf
Doctoral Symposium presentation.pdfDoctoral Symposium presentation.pdf
Doctoral Symposium presentation.pdf
 
Optimizing QoE and Latency of Live Video Streaming Using Edge Computing a...
Optimizing  QoE and Latency of  Live Video Streaming Using  Edge Computing  a...Optimizing  QoE and Latency of  Live Video Streaming Using  Edge Computing  a...
Optimizing QoE and Latency of Live Video Streaming Using Edge Computing a...
 
QoS Constrained H.264/SVC video streaming over Multicast Ad Hoc Networks
QoS Constrained H.264/SVC video streaming over Multicast Ad Hoc NetworksQoS Constrained H.264/SVC video streaming over Multicast Ad Hoc Networks
QoS Constrained H.264/SVC video streaming over Multicast Ad Hoc Networks
 
WebRTC overview
WebRTC overviewWebRTC overview
WebRTC overview
 
Immersive Video Delivery: From Omnidirectional Video to Holography
Immersive Video Delivery: From Omnidirectional Video to HolographyImmersive Video Delivery: From Omnidirectional Video to Holography
Immersive Video Delivery: From Omnidirectional Video to Holography
 
AVSTP2P Overview
AVSTP2P OverviewAVSTP2P Overview
AVSTP2P Overview
 
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual RealityFixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
 
Digital Media Production - Future Internet
Digital Media Production - Future InternetDigital Media Production - Future Internet
Digital Media Production - Future Internet
 
6NEAT project and IP..
6NEAT project and IP..6NEAT project and IP..
6NEAT project and IP..
 
Monitoring whole mpeg transport stream
Monitoring whole mpeg transport streamMonitoring whole mpeg transport stream
Monitoring whole mpeg transport stream
 
QoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
QoE- and Energy-aware Content Consumption for HTTP Adaptive StreamingQoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
QoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
 
Multi-Criteria Optimization of Content Delivery within the Future Media Internet
Multi-Criteria Optimization of Content Delivery within the Future Media InternetMulti-Criteria Optimization of Content Delivery within the Future Media Internet
Multi-Criteria Optimization of Content Delivery within the Future Media Internet
 
Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...
 
Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...Scalable Service Oriented Architecture for Audio/Video ...
Scalable Service Oriented Architecture for Audio/Video ...
 

More from Alpen-Adria-Universität

VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instancesVEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
Alpen-Adria-Universität
 
GREEM: An Open-Source Energy Measurement Tool for Video Processing
GREEM: An Open-Source Energy Measurement Tool for Video ProcessingGREEM: An Open-Source Energy Measurement Tool for Video Processing
GREEM: An Open-Source Energy Measurement Tool for Video Processing
Alpen-Adria-Universität
 
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
Alpen-Adria-Universität
 
VEEP: Video Encoding Energy and CO₂ Emission Prediction
VEEP: Video Encoding Energy and CO₂ Emission PredictionVEEP: Video Encoding Energy and CO₂ Emission Prediction
VEEP: Video Encoding Energy and CO₂ Emission Prediction
Alpen-Adria-Universität
 
Content-adaptive Video Coding for HTTP Adaptive Streaming
Content-adaptive Video Coding for HTTP Adaptive StreamingContent-adaptive Video Coding for HTTP Adaptive Streaming
Content-adaptive Video Coding for HTTP Adaptive Streaming
Alpen-Adria-Universität
 
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
Alpen-Adria-Universität
 
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Vid...
Empowerment of Atypical Viewers  via Low-Effort Personalized Modeling  of Vid...Empowerment of Atypical Viewers  via Low-Effort Personalized Modeling  of Vid...
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Vid...
Alpen-Adria-Universität
 
Optimizing Video Streaming for Sustainability and Quality: The Role of Prese...
Optimizing Video Streaming  for Sustainability and Quality: The Role of Prese...Optimizing Video Streaming  for Sustainability and Quality: The Role of Prese...
Optimizing Video Streaming for Sustainability and Quality: The Role of Prese...
Alpen-Adria-Universität
 
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
Alpen-Adria-Universität
 
Machine Learning Based Resource Utilization Prediction in the Computing Conti...
Machine Learning Based Resource Utilization Prediction in the Computing Conti...Machine Learning Based Resource Utilization Prediction in the Computing Conti...
Machine Learning Based Resource Utilization Prediction in the Computing Conti...
Alpen-Adria-Universität
 
Evaluation of Quality of Experience of ABR Schemes in Gaming Stream
Evaluation of Quality of Experience of ABR Schemes in Gaming StreamEvaluation of Quality of Experience of ABR Schemes in Gaming Stream
Evaluation of Quality of Experience of ABR Schemes in Gaming Stream
Alpen-Adria-Universität
 
Multi-access Edge Computing for Adaptive Video Streaming
Multi-access Edge Computing for Adaptive Video StreamingMulti-access Edge Computing for Adaptive Video Streaming
Multi-access Edge Computing for Adaptive Video Streaming
Alpen-Adria-Universität
 
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Alpen-Adria-Universität
 
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
Alpen-Adria-Universität
 
Energy Consumption in Video Streaming: Components, Measurements, and Strategies
Energy Consumption in Video Streaming: Components, Measurements, and StrategiesEnergy Consumption in Video Streaming: Components, Measurements, and Strategies
Energy Consumption in Video Streaming: Components, Measurements, and Strategies
Alpen-Adria-Universität
 
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Alpen-Adria-Universität
 
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
Alpen-Adria-Universität
 
HTTP Adaptive Streaming – Quo Vadis? (2023)
HTTP Adaptive Streaming – Quo Vadis? (2023)HTTP Adaptive Streaming – Quo Vadis? (2023)
HTTP Adaptive Streaming – Quo Vadis? (2023)
Alpen-Adria-Universität
 
How to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
How to Optimize Dynamic Adaptive Video Streaming? Challenges and SolutionsHow to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
How to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
Alpen-Adria-Universität
 
MPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
MPEC2: Multilayer and Pipeline Video Encoding on the Computing ContinuumMPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
MPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
Alpen-Adria-Universität
 

More from Alpen-Adria-Universität (20)

VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instancesVEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
 
GREEM: An Open-Source Energy Measurement Tool for Video Processing
GREEM: An Open-Source Energy Measurement Tool for Video ProcessingGREEM: An Open-Source Energy Measurement Tool for Video Processing
GREEM: An Open-Source Energy Measurement Tool for Video Processing
 
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
 
VEEP: Video Encoding Energy and CO₂ Emission Prediction
VEEP: Video Encoding Energy and CO₂ Emission PredictionVEEP: Video Encoding Energy and CO₂ Emission Prediction
VEEP: Video Encoding Energy and CO₂ Emission Prediction
 
Content-adaptive Video Coding for HTTP Adaptive Streaming
Content-adaptive Video Coding for HTTP Adaptive StreamingContent-adaptive Video Coding for HTTP Adaptive Streaming
Content-adaptive Video Coding for HTTP Adaptive Streaming
 
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
 
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Vid...
Empowerment of Atypical Viewers  via Low-Effort Personalized Modeling  of Vid...Empowerment of Atypical Viewers  via Low-Effort Personalized Modeling  of Vid...
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Vid...
 
Optimizing Video Streaming for Sustainability and Quality: The Role of Prese...
Optimizing Video Streaming  for Sustainability and Quality: The Role of Prese...Optimizing Video Streaming  for Sustainability and Quality: The Role of Prese...
Optimizing Video Streaming for Sustainability and Quality: The Role of Prese...
 
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
 
Machine Learning Based Resource Utilization Prediction in the Computing Conti...
Machine Learning Based Resource Utilization Prediction in the Computing Conti...Machine Learning Based Resource Utilization Prediction in the Computing Conti...
Machine Learning Based Resource Utilization Prediction in the Computing Conti...
 
Evaluation of Quality of Experience of ABR Schemes in Gaming Stream
Evaluation of Quality of Experience of ABR Schemes in Gaming StreamEvaluation of Quality of Experience of ABR Schemes in Gaming Stream
Evaluation of Quality of Experience of ABR Schemes in Gaming Stream
 
Multi-access Edge Computing for Adaptive Video Streaming
Multi-access Edge Computing for Adaptive Video StreamingMulti-access Edge Computing for Adaptive Video Streaming
Multi-access Edge Computing for Adaptive Video Streaming
 
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
 
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
 
Energy Consumption in Video Streaming: Components, Measurements, and Strategies
Energy Consumption in Video Streaming: Components, Measurements, and StrategiesEnergy Consumption in Video Streaming: Components, Measurements, and Strategies
Energy Consumption in Video Streaming: Components, Measurements, and Strategies
 
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
 
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
 
HTTP Adaptive Streaming – Quo Vadis? (2023)
HTTP Adaptive Streaming – Quo Vadis? (2023)HTTP Adaptive Streaming – Quo Vadis? (2023)
HTTP Adaptive Streaming – Quo Vadis? (2023)
 
How to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
How to Optimize Dynamic Adaptive Video Streaming? Challenges and SolutionsHow to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
How to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
 
MPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
MPEC2: Multilayer and Pipeline Video Encoding on the Computing ContinuumMPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
MPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
 

Recently uploaded

From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Product School
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
Sri Ambati
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
CatarinaPereira64715
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
DianaGray10
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
Fwdays
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
Bhaskar Mitra
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
Product School
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 

Recently uploaded (20)

From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 

Network-Assisted Delivery of Adaptive Video Streaming Services through CDN, SDN, and MEC

  • 1. Network-Assisted Delivery of Adaptive Video Streaming Services through CDN,SDN,and MEC Supervisors: Univ.-Prof.DI Dr.Hermann Hellwagner Univ.-Prof.DI Dr.Christian Timmerer Reza Farahani Klagenfurt am Wörthersee,Austria 22.08.2023 Reviewers: Prof.Dr.Filip De Turck Prof.Dr.Tobias Hoßfeld
  • 2. Table of Contents -Motivation -Technical Background -Research Questions -Contributions Introduction 1 4 2 Edge-and SDN-Assisted Frameworks for HAS 3 SFC-Enabled Architecture for HAS Collaborative Edge-Assisted Frameworks for HAS 5 Hybrid P2P-CDN Architectures for HAS 06 Conclusions 6 -Conclusions -Publications 2
  • 4. Motivation 2 3 4 5 6 1 4 ● Video is dominating today’s Internet traffic ○ Video streaming includes 66% of the total video Internet traffic [1] ○ Video-on-Demand (VoD) and live streaming have become significantly popular video streaming applications ○ Live streaming will increase 15-fold and reach 17% of Internet video traffic [2] [1] Sandvine, “The Global Internet Phenomena Report,” White Paper, 2023. https://www.sandvine.com/global-internet-phenomena-report-2023 [2] Cisco Visual Networking Index (VNI), Forecast and Trends, 2018– 2023. White Paper, 2018. https://www.cisco.com/c/en/us/solutions/collateral/executive-perspectives/annual-internet-report/white-paper-c11-741490.pdf
  • 5. HTTPAdaptive Video Streaming (HAS) 2 3 4 5 6 1 5 1 2 3 4 5 5 5 6 6 6 7 Encoder Origin Packager CDNs HTTP Res HTTP Req Reza Shokri Kalan, Reza Farahani, Emre Karsli, Christian Timmerer, and Hermann Hellwagner. Towards Low Latency Live Streaming: Challenges in a Real-world Deployment. 13th ACM MMSys, 2022. Quality Bandwidth Time Time
  • 6. Network-Assisted Video Streaming (NAVS) 2 3 4 5 6 1 6 Network Assistance by HAS Network Assistance for HAS Network Media Server
  • 7. SFC Modern NAVS Systems 2 3 4 5 6 1 7 SDN NFV Hybrid Systems NAVS Systems Networking Paradigms Content Delivery Networks Emerging Protocols Techniques Computing Continuum Nodes Edge Cloud Fog CMAF QUIC LL-HAS CMCD/SD Transcoding Multi Paradigms Hybrid P2P-CDN Caching Prefetching CDN P2P Super-Resolution Slicing
  • 8. RQ1 How can SDNs/CDNs provide assistance for HAS clients in order to improve media delivery services? Research Questions 2 3 4 5 6 1 8 How can resources (i.e., computation, storage, bandwidth) provided by the HAS clients be used to improve media delivery services? RQ2
  • 9. Research Questions 2 3 4 5 6 1 9 RQ3 RQ4 What is the utility of the proposed assistance and collaboration service? How can the utility of the proposed NAVS frameworks be thoroughly evaluated, both theoretically and practically?
  • 13. Edge and SDN-Assisted Framework for HAS 2 R. Farahani, et al. "ES-HAS: An Edge-and SDN-Assisted Framework for HTTP Adaptive Video Streaming", The 31st ACM Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), 2021. R. Farahani, et al. "CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming", IEEE 46th Conference on Local Computer Networks (LCN), 2021. 13
  • 14. Content Delivery Network (CDN) 14 3 4 5 6 1 2
  • 15. Software Defined Networking (SDN) 15 3 4 5 6 1 2 Data Plane Control Plane https://opennetworking.org/sdn-definition/
  • 16. Network Function Virtualization (NFV) 16 3 4 5 6 1 2
  • 17. SABR Framework 3 4 5 6 1 2 17 Bhat, D., Rizk, A., Zink, M. and Steinmetz, R. Network assisted content distribution for adaptive bitrate video streaming. In Proceedings of the 8th ACM MMSys, 2017. SABR: Network assisted content distribution for adaptive bitrate video streaming
  • 19. Motivation 3 4 5 6 1 2 18 Increasing the number of DASH clients ⇒ Increasing the number of exchanged messages to/from the SDN controller
  • 20. Multi-Access Edge Computing (MEC) 2 3 4 5 6 1 19 3 4 5 6 1 2
  • 21. ES-HAS System 3 4 5 6 1 2 20 ● ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming ○ Virtual Reverse Proxy (VRP) servers at the edge of an SDN-enablebd Network
  • 23. Proposed System 3 4 5 6 1 2 21 The number of messages to/from the SDN controller
  • 25. ES-HAS Server/Segment Selection Policy 3 4 5 6 1 2 23 1. RAM 2. SOM Fetching Time Quality Deviation Quality Bitrate
  • 26. ES-HAS Testbed 3 4 5 6 1 2 24 ● A cloud-based testbed, including 60 clients (Xen virtual machines) on CloudLab [1] [1] https://www.cloudlab.us/
  • 28. CSDN System 3 4 5 6 1 2 26 ● CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming ○ It equips the ES-HAS VRP with the transcoding capability
  • 30. CSDN Server/Segment Selection Policy 3 4 5 6 1 2 28 Serving Time Quality Deviation 1. When the requested quality level exist in the cache servers (Cache Hit) ○ find the cache server with minimum serving time 2. When the requested quality level is not available in any cache server (Cache Miss) ○ use replacement quality from a cache server with minimum fetch time ○ transcode the original quality from better quality level at the edge ○ fetch the original requested quality from the origin server
  • 31. CSDN Testbed 3 4 5 6 1 2 29 ● Extended ES-HAS testbed with 100 clients (Xen virtual machines) on CloudLab [1] [1] https://www.cloudlab.us/
  • 34. SFC-Enabled Architecture for HAS 3 R. Farahani, et al. "SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications", IEEE International Conference on Communications (ICC), 2023. 32
  • 35. Motivation 4 5 6 1 2 3 33 ● OTT video ● Live video streaming ● Immersive multimedia ● Video Gaming ● Video analytics for security, quality assurance, etc. Increase in amount of video generated and transported
  • 36. Motivation 4 5 6 1 2 3 33 ● OTT video ● Live video streaming ● Immersive multimedia ● Video Gaming ● Video analytics for security, quality assurance, etc. Increase in amount of video generated and transported Versatile QoE, QoS requirements Resolution (4K, 8K) Latency (LL,ULL) Bitrate
  • 37. Motivation 4 5 6 1 2 3 33 ● OTT video ● Live video streaming ● Immersive multimedia ● Video Gaming ● Video analytics for security, quality assurance, etc. Increase in amount of video generated and transported Versatile QoE, QoS requirements Resolution (4K, 8K) Latency (LL,ULL) Bitrate
  • 38. Motivation 4 5 6 1 2 3 34 SDN S F C HAS M E C ● How to leverage modern networking/computing paradigms to serve different MSs requests with acceptable QoE and improved network utilization? ● How to design a network-assisted HAS scheme without client-side modification ?
  • 39. Service Function Chaining (SFC) 4 5 6 1 2 3 35 VNF i VNF i+1 VNF n VNF i VNF i+1 VNF n SFC Chains Chain 1 Chain m … … …
  • 40. Service Function Chaining (SFC) 4 5 6 1 2 3 35 VNF i VNF i+1 VNF n VNF i VNF i+1 VNF n SFC Chains Chain 1 Chain m … … … Orchestration Placement Scheduling SFC Definition VNF Definition
  • 41. SARENAArchitecture 4 5 6 1 2 3 36 Virtual Proxy Function Virtual Cache Function Virtual Transcoding Function CDN Cache Origin Cache 1 2 3 4 5 Multimedia VNFs
  • 43. SARENA Optimization Model 4 5 6 1 2 3 38 ● The Requests Scheduler run an MILP optimization model to respond: ○ Where is the optimal place for fetching the content quality level requested by each client, while efficiently employing layers’ available resources and satisfying service requirements (e.g., service deadlines)? ○ How can we use the functions/services provided in the EL and IL layers to form MS function chains (SFCs)? ○ What is the optimal SFC for responding to the requested quality level with specific service requirements? Total MSs Serving Latency Transmitting Time Transcoding Time
  • 45. SARENATestbed 4 5 6 1 2 3 40 A cloud-based testbed, including 280 elements and real backbone topology (InternetMCI) ○ Xen virtual machines ○ 250 Dash player ○ Four Apache cache servers and an origin server ○ 19 backbone switches and 45 layer-2 links ○ Five edge server ○ Floodlight SDN controller ○ BOLA ABR algorithms ○ FFmpeg transcoders ○ LRU cache replacement policy ○ Zipf distribution is used for video and channel access popularity
  • 46. SARENATestbed 4 5 6 1 2 3 41 0.089 320 480 720 1080 1080 0.262 0.791 2.4 4.2 Resolution (p) Bitrate (Mbps) Bitrate (Mbps) Resolution (p) 20 VoDs, 300 sec. duration, 4 sec. segments 320 480 720 720 1080 1080 1080 0.128 0.32 0.78 1.4 2.4 3.3 3.9 5 live ch, 300 sec. duration, 2 sec. segments
  • 47. Evaluation Methods and Metrics 4 5 6 1 2 3 41 ✔ Baseline systems: ◆ CDN-assisted (CDA) ◆ Non VNF-assisted (NVA) ◆ Non VTF-enabled (NTE) ◆ Non Reconfiguration-enabled (NRE) ✔ The performance of the aforementioned approaches is evaluated through ◆ ASB: Average Segment Bitrate ◆ AQS: Average Number of Quality Switches ◆ ANS: Average Number of Stalls ◆ ASD: Average Stall Duration ◆ APQ: Average Perceived QoE calculated by ITU-T P.1203 mode 0 [1] ◆ ASL: Overall time for serving ◆ NCV: Network Cost Value ◆ ETR: Edge/P2P Transcoding Ratio ◆ BTL: Backhaul Traffic Load [1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
  • 48. SARENA Results 4 5 6 1 2 3 42 ASB: Average Segment Bitrate AQS: Average Number of Quality Switches ANS: Average Number of Stalls ASD: Average Stall Duration APQ: Average Perceived QoE calculated by ITU-T P.1203 mode 0 [1] ASL: Average Serving Latency [1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
  • 49. SARENA Results 4 5 6 1 2 3 43 NCV: Network Cost Value ETR: Edge Transcoding Ratio BTL: Backhaul Traffic Load
  • 50. Collaborative Edge-Assisted Frameworks for HAS 4 R. Farahani, et al., "LEADER: A Collaborative Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming". IEEE International Conference on Communications (ICC), 2022. R. Farahani, et al., "ARARAT: A Collaborative Edge-Assisted Framework for HTTP Adaptive Video Streaming", IEEE Transactions on Network and Service Management (TNSM), 2022.
  • 51. 5 6 1 2 3 4 45 Motivation ✔ Establish a collaboration between edge servers to use their potential idle resources for serving HAS clients. M E C SDN N F V H A S
  • 53. 5 6 1 2 3 4 47 LEADER/ARARATARCHITECTURE ✔ MEC Servers: ◆ Local Edge Server (LES) ◆ Neighboring Edge Server (NES) ✔ Virtualized Edge Functions: ◆ Partial Cache (PC) ◆ Video Transcoder (Tran) Edge Layer
  • 56. LEADER and ARARATAction Tree 4 5 6 1 2 3 48 5 6 1 2 3 4 LEADER Action Tree ARARAT Action Tree
  • 57. LEADER/ARARAT Optimization Models 4 5 6 1 2 3 49 ● The SDN controller run an MILP optimization model to respond: ○ Where is the optimal place (i.e., LES, NESs, CSs, or the origin server) in terms of the following items for fetching each client’s requested content quality level from? ■ minimum serving time (LEADER) ■ minimum serving time and minimum network cost (ARARAT) ○ What is the optimal approach for responding to the requested quality level (i.e., fetch or transcode)? Serving Latency 5 6 1 2 3 4 Network Cost LEADER ARARAT
  • 58. ARARAT Coarse-Grained (CG) Heuristic 4 5 6 1 2 3 49 5 6 1 2 3 4 COM → LOM
  • 59. ARARAT Fine-Grained I (FG I) Heuristic 4 5 6 1 2 3 50 5 6 1 2 3 4 LOM → EFG I
  • 60. ARARAT Fine-Grained I (FG I) Heuristic 4 5 6 1 2 3 50 5 6 1 2 3 4 LOM → EFG I Network bandwidth allocation?
  • 61. ARARAT Fine-Grained II (FG II) Heuristic 4 5 6 1 2 3 51 5 6 1 2 3 4 EFG I → EFG II
  • 62. ARARAT Fine-Grained II (FG II) Heuristic 4 5 6 1 2 3 52 5 6 1 2 3 4 The bandwidth allocation is modeled as a “Fairness LP Optimization Model”
  • 63. ARARATTestbed 1 53 ● A cloud-based testbed, including 301 elements (Xen virtual machines) and real backbone topology (Geant and Abilene) 4 5 6 1 2 3 5 6 1 2 3 4
  • 64. 1 54 4 5 6 1 2 3 5 6 1 2 3 4 Evaluation Methods ✔ SABR: ◆ Non edge-enabled system ✔ ES-HAS ◆ Non edge-collaborative and transcoding-enabled system ◆ Each edge runs an MILP model on the collected client requests to serve them via one of actions 1, 7, or 9 ✔ CSDN ◆ Non-collaborative approach ◆ Each edge server runs an MILP model for the collected client requests and serves them separately via one of the actions 1, 2, 7, 8 or 9 ✔ NECOL ◆ The Non Edge Collaborative (NECOL) system does not support an edge collaboration. ◆ Each NECOL edge server executes a simplified version of the proposed FG I heuristic for ◆ each client request to serve it through one of the actions 1, 2, 7, 8 or 9 ✔ DECOL ◆ Default Edge Collaborative (DECOL) ◆ Run the proposed FG I heuristic
  • 65. 1 55 4 5 6 1 2 3 5 6 1 2 3 4 LEADER Results ASB: Average Segment Bitrate AQS: Average Number of Quality Switches ANS: Average Number of Stalls ASD: Average Stall Duration APQ: Average Perceived QoE calculated by ITU-T P.1203 mode 0 [1] CHR: Cache Hit Ratio ETR: Edge Transcoding Ratio BTL: Backhaul Traffic Load [1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
  • 66. 1 56 4 5 6 1 2 3 5 6 1 2 3 4 ARARAT Results ASB: Average Segment Bitrate AQS: Average Number of Quality Switches ANS: Average Number of Stalls ASD: Average Stall Duration APQ: Average Perceived QoE calculated by ITU-T P.1203 mode 0 [1] [1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
  • 67. 1 57 4 5 6 1 2 3 5 6 1 2 3 4 ARARAT Results CHR: Cache Hit Ratio ETR: Edge Transcoding Ratio BTL: Backhaul Traffic Load ANU: Average Network Utilization ASL: Average Serving Time NCV: Network Cost Value ANC: Average Number of Communicated messages from/to the SDN controller
  • 68. Hybrid P2P-CDN Architectures for HAS 5 R. Farahani, et al., "Hybrid P2P-CDN Architecture for Live Video Streaming: An Online Learning Approach”. IEEE Global Communications Conference (GLOBECOM), 2022. R. Farahani, et al., "RICHTER: Hybrid P2P- CDN Architecture for Low Latency Live Video Streaming”. ACM Mile-High Video Conference (MHV), 2022. R. Farahani, et al., "ALIVE: A Latency- and Cost-Aware Hybrid P2P-CDN Framework for Live Video Streaming", submitted to IEEE Transactions on Network and Service Management (TNSM), 2023.
  • 70. Motivation 6 1 2 3 4 5 60 ✔ Employ all potential resources (storage, bandwidth, computation) of the P2P network ✔ Utilize P2P and CDN resources efficiently ✔ Satisfy HAS client requests with acceptable QoE and improved latency CDN P2P
  • 72. ALIVE Architecture 6 1 2 3 4 5 62 ✔ RICHTER does not include the PSR function.
  • 73. RICHTER and ALIVE Action Tree 63 RICHTER Action Tree ALIVE Action Tree 6 1 2 3 4 5
  • 74. RICHTER/ALIVE Optimization Models 4 5 6 1 2 3 64 ● The VTS server must respond: ○ Where is the optimal place (i.e., adjacent peers, VTS, CDN servers, or origin server) in terms of the following items for fetching each client’s requested content quality level from? ■ minimum serving time (RICHTER) ■ minimum serving time and minimum network cost (ALIVE) ○ What is the optimal approach for responding to the requested quality level (i.e., fetch ,transcode, or upscale)? Serving Latency 5 6 1 2 3 4 Network Cost RICHTER ALIVE 6 1 2 3 4 5
  • 75. RICHTER Online Learning (OL) Approach 4 5 6 1 2 3 65 ● Leverage new modules, classification technique to introduce an OL heuristic approach ● Self Organizing Map (SOM) is adopted as the request management solution in the OL agent: ○ popular technique for unsupervised classification problems ○ can be applied to solve NP-hard problems ○ does not require a prepared dataset for supervised model training ● Alive runs a simplified version that is based on the Greedy approach 5 6 1 2 3 4 6 1 2 3 4 5 Node Action Req# Violation
  • 76. ALIVE Greedy-Based Heuristic Approach 4 5 6 1 2 3 65 5 6 1 2 3 4 6 1 2 3 4 5
  • 77. ALIVE Testbed 4 5 6 1 2 3 66 5 6 1 2 3 4 6 1 2 3 4 5 ● A cloud-based testbed, including 375 elements (Xen virtual machines) and real backbone topology (InternetMCI) ● Apple M1, Xiaomi Mi11, and iPhone 11
  • 78. 67 Evaluation Methods ✔ NOH: ◆ Non Hybrid system like traditional CDN based methods ✔ SEH: ◆ Simple Edge-enabled Hybrid ◆ It employs a simple VTS server without caching and transcoding capabilities ✔ NTH ◆ Non Transcoding-enabled Hybrid ◆ It has a VTS server with only caching capability ✔ ECT ◆ Edge Caching/Transcoding Hybrid ◆ It does not include transcoding and super-resolution at the peer side ✔ NSH ◆ Non SR-enabled Hybrid (RICHTER using Greedy apprach) ◆ There is no super-resolution feature on the peer side 4 5 6 1 2 3 5 6 1 2 3 4 6 1 2 3 4 5
  • 80. 69 RICHTER Results 4 5 6 1 2 3 5 6 1 2 3 4 6 1 2 3 4 5 ASB: Average Segment Bitrate AQS: Average Number of Quality Switches ANS: Average Number of Stalls ASD: Average Stall Duration APQ: Average Perceived QoE calculated by ITU-T P.1203 mode 0 [1] ASL: Average Serving Time CHR: Cache Hit Ratio ETR: Edge Transcoding Ratio BTL: Backhaul Traffic Load [1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
  • 81. 70 ALIVE Results 4 5 6 1 2 3 5 6 1 2 3 4 6 1 2 3 4 5 ASB: Average Segment Bitrate AQS: Average Number of Quality Switches ANS: Average Number of Stalls ASD: Average Stall Duration ASL: Average Serving Time APQ: Average Perceived QoE calculated by ITU-T P.1203 mode 0 [1] [1] https://www.itu.int/net4/ipr/details_ps.aspx?sector=ITU-T&id=P1203-01
  • 82. 71 ALIVE Results 4 5 6 1 2 3 5 6 1 2 3 4 6 1 2 3 4 5 CHR: Cache Hit Ratio ETR: Edge Transcoding Ratio PTSR: Peer SR and TR Ratio BTL: Backhaul Traffic Load EEC: Edge Energy Consumption for running ETR NCV: Network Cost Value
  • 84. Conclusions How can SDNs/CDNs provide assistance for HAS clients in order to improve media delivery services? RQ1 1 2 3 4 5 6 73 ● ES-HAS and CSDN frameworks ○ Introduce Virtual Reverse Proxy function to act as a gateway between HAS clients and the network ○ Design new server/segment selection policies ● SARENA framework ○ Design VNFs that can be chained under an SDN controller’s coordination to establish different types of video streaming services ● LEADER and ARARAT frameworks ○ Establish a collaboration between edge servers under an SDN controller’s coordination ○ Propose Action Tree including all possible actions to serve requests ○ Propose fair bandwidth allocation startegies
  • 85. Conclusions How can resources (i.e., computation, storage, bandwidth) provided by the HAS clients be used to improve media delivery services? RQ2 1 2 3 4 5 6 74 ● RICHTER and ALIVE frameworks ○ Hybrid P2P-CDN NAVS systems for HAS clients in live streaming applications ○ Employing idle computational resources and available bandwidth of HAS clients (i.e., peers) to offer distributed video processing services, such as video transcoding and video super- resolution. ○ Propose Action Tree including all possible actions to serve requests ○ Propose heuristic algorithms to play decision-maker roles in large-scale practical scenarios.
  • 86. Conclusions What is the utility of the proposed assistance and collaboration service? RQ3 1 2 3 4 5 6 75 ● User QoE metrics (application QoS) ○ quality bitrate, number of quality switches, number of stalls, stalling duration, serving times, VMAF values, standardized perceived quality. ● Network utilization metrics ○ cache hit ratio, transcoding ratio at the edge, transcoding ratio at the P2P network, super-resolution ratio at the P2P network, computational cost, backhaul bandwidth cost, number of communicated messages to/from the SDN controller. ● Algorithm performance metrics ○ execution times and objective function values
  • 87. Conclusions RQ4 1 2 3 4 5 6 76 How can the utility of the proposed NAVS frameworks be thoroughly evaluated, both theoretically and practically? ● Desine cloud-based testbeds to run realistic network topologies for all proposed frameworks ○ Use tens/hundreds of elements, each of which runs Linux-based operating systems inside Xen virtual machines. ○ Use two different ABR algorithm ○ Employ bitrate ladders of real video datasets ○ Use OpenFlow backbone switches and Floodlight SDN controller ○ Use realistic network traces, tools, and assumptions ○ Compare results with state-of-the-art and baseline approaches
  • 88. First Author Publications 77 1. R. Farahani, E. Cetinkaya, C. Timmerer, M. Shojafar, M. Ghanbari, H. Hellwagner. ALIVE: A Latency- and Cost-Aware Hybrid P2P-CDN Framework for Live Video Streaming. Submitted to IEEE Transactions on Network and Service Management (TNSM), 2023. 2. R. Farahani, C. Timmerer, H. Hellwagner. Towards Low-Latency and Energy-Efficient Hybrid P2P-CDN Live Video Streaming. Submitted to IEEE COMSOC MMTC Communication-Frontiers, 2023. 3. R. Farahani, M. Shojafar, C. Timmerer, F. Tashtarian, M. Ghanbari, H. Hellwagner. ARARAT: A Collaborative Edge-Assisted Framework for HTTP Adaptive Video Streaming. IEEE Transactions on Network and Service Management (TNSM), 2022. 4. R. Farahani, A. Bentaleb, C. Timmerer, M. Shojafar, R. Prodan, H. Hellwagner. SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications. IEEE International Conference on Communications (ICC), 2022. 5. R. Farahani, A. Bentaleb, E. Cetinkaya, C. Timmerer, R. Zimmermann, H. Hellwagner. Hybrid P2P-CDN Architecture for Live Video Streaming: An Online Learning Approach. IEEE Global Communications Conference (GLOBECOM), 2022. 6. R. Farahani, F. Tashtarian, C. Timmerer, M. Ghanbari, H. Hellwagner. LEADER: A Collaborative Edge- and SDN-Assisted Framework for HTTP Adaptive Video. IEEE International Conference on Communications (ICC), 2022. 7. R. Farahani, F. Tashtarian, H. Amirpour, C. Timmerer, M. Ghanbari, H. Hellwagner. CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming. 46th IEEE Conference on Local Computer Networks (LCN), 2021. 8. R. Farahani, F. Tashtarian, A. Erfanian, C. Timmerer, M. Ghanbari, H. Hellwagner. ES-HAS: an edge- and SDN-assisted framework for HTTP adaptive video streaming. 31st ACM Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), 2021. 9. R. Farahani. CDN and SDN Support and Player Interaction for HTTP Adaptive Video Streaming. 12th ACM Multimedia Systems Conference (MMSys), 2021. 10. R. Farahani, A. Bentaleb, M. Shojafar, H. Hellwagner. CP-Steering: CDN- and Protocol-Aware Content Steering Solution for HTTP Adaptive Video Streaming. ACM Mile High Video (MHV), 2023. 11. R. Farahani, H. Amirpour, F. Tashtarian, A.Bentaleb, C. Timmerer, H. Hellwagner, and R. Zimmermann. RICHTER: Hybrid P2P-CDN Architecture for Low Latency Live Video Streaming. ACM Mile-High Video (MHV), 2022.
  • 89. Co-authored Publications 78 1. V. V Menon, R. Farahani, P. T Rajendran, H. Hellwagner, M. Ghanbari, C. Timmerer. Reduced Reference Transcoding Quality Prediction for Video Streaming Applications. ACM Mile High Video (MHV), 2023. 2. V. V Menon, P. T Rajendran, R. Farahani, K. Schöffmann, C. Timmerer. Video Quality Assessment with Texture Information Fusion for Streaming Applications. Submitted to the IEEE International Conference on Visual Communications and Image Processing (VCIP), 2023. 3. V. V Menon, R. Farahani, P. T Rajendran, S. Afzal, K. Schöffmann, C. Timmerer. Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Streaming. Submitted to the IEEE International Conference on Visual Communications and Image Processing (VCIP), 2023. 4. S. Chellappa, R. Farahani, R. Bartos, H. Hellwagner. Context-Aware HTTP Adaptive Video Streaming Utilizing QUIC’s Stream Priority. ACM Mile High Video (MHV), 2023. 5. A. Bentaleb, R. Farahani, F. Tashtarian, H. Hellwagner, R.Zimmermann. Which CDN to Download From? A Client and Server Strategies. ACM Mile High Video (MHV), 2023. 6. R. Shokri Kalan, R. Farahani, E. Karsli, C. Timmerer, H. Hellwagner. Towards Low Latency Live Streaming: Challenges in Real-World Deployment. The 13th ACM Multimedia Systems Conference (MMSys), 2022. 7. F. Tashtarian, A. Bentaleb, R. Farahani, M. Nguyen, C. Timmerer, H.Hellwagner, R. Zimmermann. A Distributed Delivery Architecture for User Generated Content Live Streaming over HTTP. IEEE 46th Conference on Local Computer Networks (LCN), 2021. 8. A. Erfanian, F. Tashtarian, R. Farahani, C. Timmerer, H. Hellwagner. On Optimizing Resource Utilization in AVC-based Real-time Video Streaming. The 6th IEEE Conference on Network Softwarization (NetSoft), 2020.
  • 91. Future Directions Traffic Encryption Immersive Streaming Emerging Protocols Grean Streaming
  • 92. RICHTER Online Learning (OL) Approach 4 5 6 1 2 3 65 ● Leverage new modules, classification technique to introduce an OL heuristic approach ● Self Organizing Map (SOM) is adopted as the request management solution in the OL agent: ○ popular technique for unsupervised classification problems ○ can be applied to solve NP-hard problems ○ does not require a prepared dataset for supervised model training ● Alive runs a simplified version that is based on the Greedy approach 5 6 1 2 3 4 6 1 2 3 4 5 Node Action Req# Violation
  • 93. Statistics Calculation IM= (New Value - Old Value) / Old Value
  • 96. ES-HAS Results 3 4 5 6 1 2 ● We analyze the Impact of different parameters on ES-HAS MILP model behavior by: ○ ACS : the average usage percentage of cache servers with the shortest fetch time ○ AMD: the average (for different accepted max-deviation value) of the maximum deviation between requested quality and forwarded quality ○ AQB: the average of the video quality bitrate for all received segments in Mbps
  • 97. Problem Formulation Central MILP Optimization Model Constraints & Objective Function ✓ Resource Map ✓ Requests ✓ Videos Information ✓ Computational Cost Optimal action for each request
  • 98. Fine-Grained II (FG II)-- Bandwidth Allocation Strategy BwAllocation request Minimum fairness value among all fairness coefficient. ✔ The bandwidth allocation is modeled as a “Fairness LP Optimization Model” The fairness coefficient to the shared link(a, b) in the route between i and j. The allocated bandwidth to the shared link(a, b) in the route between i and j. 98
  • 100. Evaluation Results-- Scenario I ✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG approaches in terms of: ◆ ETV: Execution Time Values for the different ARARAT schemes. ◆ NOV: Normalized Objective Value for the ARARAT schemes.
  • 101. Evaluation Results-- Scenario I ✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG approaches in terms of: ◆ ETV: Execution Time Values for the different ARARAT schemes. ◆ NOV: Normalized Objective Value for the ARARAT schemes.
  • 102. Evaluation Results-- Scenario I ✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG approaches in terms of: ◆ ETV: Execution Time Values for the different ARARAT schemes. ◆ NOV: Normalized Objective Value for the ARARAT schemes.
  • 103. Evaluation Results-- Scenario I ✔ This scenario compares the proposed centralized optimization MILP model and the CG and FG approaches in terms of: ◆ ETV: Execution Time Values for the different ARARAT schemes. ◆ NOV: Normalized Objective Value for the ARARAT schemes.