ºÝºÝߣ

ºÝºÝߣShare a Scribd company logo

Livestream Video P2P

•Download as PPT, PDF•
•
Vlad Vega
Vlad Vega

The document discusses optimization concepts for peer-to-peer video streaming including scalable video coding, network coding, and mesh architectures. An implementation was created using these concepts with 1000 peers streaming 3 videos at different bitrates. The results showed that using scalable video coding and network coding increased video quality and throughput, especially under high churn rates and flash crowds. Optimal block and segment sizes for network coding were also determined.

1 of 16
P2p Video Streaming Intro to P2P Networks. Intro to P2P Video Stream. Optimization Concepts. The Implemented study. Results of the study. DATE: 11/30/10 VLADIMIR BUKHIN CONTENTS: AUTHOR: VLADIMIR BUKHIN DATE: 11/30/10
Defining p2p Distributed Architecture that partitions tasks between peers. Peers act as clients and servers. Consumers and Suppliers. DATE: 11/30/10 VLADIMIR BUKHIN
p2p usage File Sharing: Napster, Kazaa, LimeWire BitTorrent!!! Streaming Music: LiveStation, Spotify Other YaCy (P2P search Engine) DATE: 11/30/10 VLADIMIR BUKHIN
Intro to Live Stream Implemented systems: SopCast, TVAnts, PPLive. Challenges: Heterogeneity of Peers. High Churn Rate Solutions: Utilize peers efficiently. Support diverse receiver resources. Quickly adapt to network dynamics. DATE: 11/30/10 VLADIMIR BUKHIN
Optimization concepts Scalable Video Coding: SL approach waists bandwidth. 31 possible layers in H.264/SVC standard. Temporal-> frame rate (7) Spatial-> resolution (8) Quality-> Granularity (16) Predictability DATE: 11/30/10 VLADIMIR BUKHIN
Mesh VS Tree Differences Management cost. Churn rate handling Parent dependency. DATE: 11/30/10 VLADIMIR BUKHIN
Random Network Coding Send partial data. Many peers upload. Greater Throughput. DATE: 11/30/10 VLADIMIR BUKHIN
Sender NC process Sender Encoding: Data broken into blocks. Random blocks encoded. Coefficients attached and packets sent. DATE: 11/30/10 VLADIMIR BUKHIN BLOCKS OF DATA: b 1, b 2 , b 3 ,...,b n. VECTOR OF COEF: C=[0 1 0 1 0 0 1 0] LINEAR ENCODING:
Receiver decoding Receiver decoding: Downloads Linear combinations. Use Guassian Elimination if m>n. Solves for unknowns Progressively Negligible dependency rate. DATE: 11/30/10 VLADIMIR BUKHIN EXAMPLE MATRIX: [1 0 1 0 0 0 0 0][X 1 ] [0 1 1 0 0 0 0 0][X 2 ] [1 1 0 0 0 0 0 0][X 3 ] ... [0 0 0 1 1 1 0 0][X 8 ]
Peer process Full Peer Process: DATE: 11/30/10 VLADIMIR BUKHIN
The Implementation Three Video chosen with 850, 500, and 325 Kbps. 1000 peers join at random, 10% leave the system. Experiments with high churn rates and flash crowds. DATE: 11/30/10 VLADIMIR BUKHIN VARIATIONS TESTED: 1. SVC + NC 2. SVC 3. SL + NC 4. SL
Results DATE: 11/30/10 VLADIMIR BUKHIN Average Stream Rate Average Stream Quality
high churn rate DATE: 11/30/10 VLADIMIR BUKHIN High Churn Rate Flash Crowds
nc size results Optimal Block Size: 512 bytes. Optimal Segment Size= ((Video Bit Rate)/8)*(optimal segment time) = 100- 200kB DATE: 11/30/10 VLADIMIR BUKHIN
Summary The use of: Scalable Video Coding. Network Coding. A mesh unidirectional p2p architecture. Will: Increase video streaming quality. Raise streaming throughput. Use joining peer resources efficiently. DATE: 11/30/10 VLADIMIR BUKHIN
References Shabnam Mirshokraie and Mohamed Hefeeda. 2010. Live peer-to-peer streaming with scalable video coding and networking coding. In Proceedings of the first annual ACM SIGMM conference on Multimedia systems (MMSys '10). ACM, New York, NY, USA, 123-132. Chen Feng and Baochun Li. 2008. On large-scale peer-to-peer streaming systems with network coding. In Proceeding of the 16th ACM international conference on Multimedia (MM '08). ACM, New York, NY, USA, 269-278. Schwarz, H.; Marpe, D.; Wiegand, T.; , "Overview of the Scalable Video Coding Extension of the H.264/AVC Standard," Circuits and Systems for Video Technology, IEEE Transactions on , vol.17, no.9, pp.1103-1120, Sept. 2007 Wang, N.; Ansari, N.; , "Downloader-Initiated Random Linear Network Coding for Peer-to-Peer File Sharing," Systems Journal, IEEE , vol.PP, no.99, pp.1-1, 0 Kim, MinJi; Sundararajan, Jay Kumar; Medard, Muriel; , "Network Coding for Speedup in Switches," Information Theory, 2007. ISIT 2007. IEEE International Symposium on , vol., no., pp.1086-1090, 24-29 June 2007 Google Images. 11/26/10 http://en.wikipedia.org/wiki/Peer-to-peer , 11/26/10 DATE: 11/30/10 VLADIMIR BUKHIN

More Related Content

Livestream Video P2P

  • 1. P2p Video Streaming Intro to P2P Networks. Intro to P2P Video Stream. Optimization Concepts. The Implemented study. Results of the study. DATE: 11/30/10 VLADIMIR BUKHIN CONTENTS: AUTHOR: VLADIMIR BUKHIN DATE: 11/30/10
  • 2. Defining p2p Distributed Architecture that partitions tasks between peers. Peers act as clients and servers. Consumers and Suppliers. DATE: 11/30/10 VLADIMIR BUKHIN
  • 3. p2p usage File Sharing: Napster, Kazaa, LimeWire BitTorrent!!! Streaming Music: LiveStation, Spotify Other YaCy (P2P search Engine) DATE: 11/30/10 VLADIMIR BUKHIN
  • 4. Intro to Live Stream Implemented systems: SopCast, TVAnts, PPLive. Challenges: Heterogeneity of Peers. High Churn Rate Solutions: Utilize peers efficiently. Support diverse receiver resources. Quickly adapt to network dynamics. DATE: 11/30/10 VLADIMIR BUKHIN
  • 5. Optimization concepts Scalable Video Coding: SL approach waists bandwidth. 31 possible layers in H.264/SVC standard. Temporal-> frame rate (7) Spatial-> resolution (8) Quality-> Granularity (16) Predictability DATE: 11/30/10 VLADIMIR BUKHIN
  • 6. Mesh VS Tree Differences Management cost. Churn rate handling Parent dependency. DATE: 11/30/10 VLADIMIR BUKHIN
  • 7. Random Network Coding Send partial data. Many peers upload. Greater Throughput. DATE: 11/30/10 VLADIMIR BUKHIN
  • 8. Sender NC process Sender Encoding: Data broken into blocks. Random blocks encoded. Coefficients attached and packets sent. DATE: 11/30/10 VLADIMIR BUKHIN BLOCKS OF DATA: b 1, b 2 , b 3 ,...,b n. VECTOR OF COEF: C=[0 1 0 1 0 0 1 0] LINEAR ENCODING:
  • 9. Receiver decoding Receiver decoding: Downloads Linear combinations. Use Guassian Elimination if m>n. Solves for unknowns Progressively Negligible dependency rate. DATE: 11/30/10 VLADIMIR BUKHIN EXAMPLE MATRIX: [1 0 1 0 0 0 0 0][X 1 ] [0 1 1 0 0 0 0 0][X 2 ] [1 1 0 0 0 0 0 0][X 3 ] ... [0 0 0 1 1 1 0 0][X 8 ]
  • 10. Peer process Full Peer Process: DATE: 11/30/10 VLADIMIR BUKHIN
  • 11. The Implementation Three Video chosen with 850, 500, and 325 Kbps. 1000 peers join at random, 10% leave the system. Experiments with high churn rates and flash crowds. DATE: 11/30/10 VLADIMIR BUKHIN VARIATIONS TESTED: 1. SVC + NC 2. SVC 3. SL + NC 4. SL
  • 12. Results DATE: 11/30/10 VLADIMIR BUKHIN Average Stream Rate Average Stream Quality
  • 13. high churn rate DATE: 11/30/10 VLADIMIR BUKHIN High Churn Rate Flash Crowds
  • 14. nc size results Optimal Block Size: 512 bytes. Optimal Segment Size= ((Video Bit Rate)/8)*(optimal segment time) = 100- 200kB DATE: 11/30/10 VLADIMIR BUKHIN
  • 15. Summary The use of: Scalable Video Coding. Network Coding. A mesh unidirectional p2p architecture. Will: Increase video streaming quality. Raise streaming throughput. Use joining peer resources efficiently. DATE: 11/30/10 VLADIMIR BUKHIN
  • 16. References Shabnam Mirshokraie and Mohamed Hefeeda. 2010. Live peer-to-peer streaming with scalable video coding and networking coding. In Proceedings of the first annual ACM SIGMM conference on Multimedia systems (MMSys '10). ACM, New York, NY, USA, 123-132. Chen Feng and Baochun Li. 2008. On large-scale peer-to-peer streaming systems with network coding. In Proceeding of the 16th ACM international conference on Multimedia (MM '08). ACM, New York, NY, USA, 269-278. Schwarz, H.; Marpe, D.; Wiegand, T.; , "Overview of the Scalable Video Coding Extension of the H.264/AVC Standard," Circuits and Systems for Video Technology, IEEE Transactions on , vol.17, no.9, pp.1103-1120, Sept. 2007 Wang, N.; Ansari, N.; , "Downloader-Initiated Random Linear Network Coding for Peer-to-Peer File Sharing," Systems Journal, IEEE , vol.PP, no.99, pp.1-1, 0 Kim, MinJi; Sundararajan, Jay Kumar; Medard, Muriel; , "Network Coding for Speedup in Switches," Information Theory, 2007. ISIT 2007. IEEE International Symposium on , vol., no., pp.1086-1090, 24-29 June 2007 Google Images. 11/26/10 http://en.wikipedia.org/wiki/Peer-to-peer , 11/26/10 DATE: 11/30/10 VLADIMIR BUKHIN