Download
how to meet the deadline for packet video n.
Skip this Video
Loading SlideShow in 5 Seconds..
How to Meet the Deadline for Packet Video PowerPoint Presentation
Download Presentation
How to Meet the Deadline for Packet Video

How to Meet the Deadline for Packet Video

125 Vues Download Presentation
Télécharger la présentation

How to Meet the Deadline for Packet Video

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. How to Meet the Deadlinefor Packet Video Bernd Girod Mark Kalman Eric Setton Information Systems Laboratory Stanford University

  2. THE MEANING OF FREE SPEECH The acquisition by eBay of Skype is a helpful reminder to the world's trillion-dollar telecoms industry that all phone calls will eventually be free . . . . . . Ultimately—perhaps by 2010—voice may become a free internet application, with operators making money from related internet applications like IPTV . . . [Economist, September 2005]

  3. IPTV is Becoming a Reality Verizon 10M IPTV households by 2009 SBC (ATT) 18M IPTV households by 2007 [IEEE Spectrum, Jan. 2005]

  4. Why Is Internet Video Hard? Internet is a best-effort network . . . CongestionInsufficient rate to carry all traffic Packet loss Impairs perceptual quality Delay Impairs interactivity of services; Zapping < 500 ms

  5. How to Meet the Deadline for Packet Video

  6. Internet How to Meet the Deadline for Packet Video

  7. How to Meet the Deadline for Packet Video • Congestion, QoS, and “fair” sharing • Maximum-utility resource allocation for multiple video streams • Example: video over wireless home networks • Congestion-distortion optimized packet scheduling (CoDiO) • Example: P2P multicasting of live video • Packet scheduling for multicast trees

  8. Measuring Congestion E[Delay] “Congestion” Traffic flow • Congestion in packet-switched network: • queuing delay that packets experience, • weighted by size of the packet • averaged over all packets in the network

  9. Congestion GrowsNonlinearly with Link Utilization Congestion D [seconds] C Rate R

  10. How 1B Users Share the Internet Rate R TCP Throughput maximum transfer unit Growing congestion data rate packet loss rate p round trip time 0.0001 0.001 0.01 0.1 [Mahdavi, Floyd, 1997] [Floyd, Handley, Padhye, Widmer, 2000]

  11. Reservation-ism Voice and video need guaranteed QoS (bandwidth, loss, delay) Requires admission control: “Busy tone” when network is full Best effort is fine for data applications Best Effort-ism Best Effort good enough for all applications Real-time applications can be made adaptive to cope with any level of service Overprovisioning always solves the problem, and it’s cheaper than QoS guarantees QoS vs. Best Effort

  12. Simple Model of A Shared Link • Link of capacity C is shared among k flows • Fair sharing: each admitted flow uses rate R=C/k • Homogeneous flows with same utility function u(R) • Total utility C [Breslau, Shenker, 1998]

  13. Rigid Applications u • Utility u=0 below of minimum bit-rate B • Admit at most flows • With sufficient overprovisioning, no admission control needed, since 1 C/k B

  14. Elastic Applications • Elastic applications: convex utility function u(R) • All flows should be admitted: best effort! u(R) R

  15. H.264 video coding for 2 different testsequences Video is elastic application. . . above a certain minimum quality Bottleneck links: admission control and dynamic rate control combined Rate must be adapted to network throughput. How? Utility function depends on content: should use unequal rate allocation QoS vs. Best Effort for Video Good picture quality Foreman Mobile Bad picture quality

  16. Different Utility Functions • Better than utility-oblivious “fair” sharing • With rk>=0  Karush-Kuhn-Tucker conditions uk Equal-slope “Pareto condition” Vilfredo Pareto 1848-1923 rk

  17. Distribution of TV over WLAN 5 Mbps 11 Mbps 2 Mbps Home Media Gateway [courtesy: van Beek, 2004]

  18. Video over WLAN Network Interface playout buffer 802.11b Transcoder Receiver Decoder Video encoded at higher rate Wireless Terminal Controller [Kalman, van Beek, Girod 2005]

  19. Video over WLAN with Multiple Streams Transcoder Decoder 0 c0 0 Network Interface Transcoder Receiver … 1 Decoder c1 1 … … (Multi-Channel) … Transcoder M cM Decoder M Controller Wireless terminals [Kalman, van Beek, Girod 2005]

  20. Dynamic Estimation of R-D Curve Scene cuts R-D Model [Stuhlmüller et al. 2000] Parameters track weighted average of last I-Frame, P-Frame and B-Frame Rate 

  21. 802.11b Transmission of 2 Video Streams Link rates [kbps] Channeltimeallocation Transcoderbit-rate[kbps] Backlogin frames PSNRin dB

  22. Self congestioncauses late loss Video Distortion with SelfCongestion Good Picture quality Bad picture quality Bit-Rate [kbps]

  23. Effect of Playout Delay and Loss Sensitivity Foreman Salesman 10% 40% headroom Simulations over ns-2 Link capacity 400 kb/s

  24. 1 sender Simulation of 600 kbps link Latency 400 msec 380 kbps, 36 dB Highest sustainable video quality 420 kbps, 33.7 dB

  25. Modeling Self-Congestionfor Packet Scheduling • Rate-distortion optimized packet scheduling (RaDiO) typically assumes independent delay pdfs for successive packet transmissions [Chou, Miao, 2001] • Model delay pdf by exponential with varying shift Probability distribution delay [Setton, Girod, 2004]

  26. B B I B B B P I I P B B P B I B B CoDiO Light Scheduler I B B P B Pictures to send Schedule

  27. CoDiO Scheduling Performance Mother & Daughter News 30 % 25 % Playout deadline (s) Playout deadline (s) Simulations over ns-2 Packet loss rate 2% Bandwidth 400 kb/s Propagation delay: 50ms

  28. CoDiO ARQ H.264/AVC @250 kb/s Link rate 400 kb/s, propagation delay 50 ms 2 % packet loss0.6 second playout deadline

  29. 60 % CoDiO vs. RaDiO Playout deadline (s) Playout deadline (s) Sequence: Foreman Packet loss rate 2% Link capacity 400 kb/s Propagation delay: 50ms Playout deadline (s)

  30. Video stream … … Video Multicast over P2P Networks Challenges • Limited bandwidth • Delay due to multi-hop transmission • Unreliability of peers Our Approach [Setton, Noh, Girod, 2005] • Determine encoding rate as a function of network bandwidth • Build and maintain complementary multicast trees • Adapt media scheduling to network conditions and to content • Request retransmissions to mitigate losses Related work • [Chu, Rao, Zhang, 2000] • [Padmanabhan, Wang and Chou, 2003] • [Guo, Suh, Kurose, Towsley, 2003] • [Cui, Li, Nahrstedt, 2004] • [Do, Hua, Tantaoui, 2004] • [Hefeeda, Bhargava, Yau, 2004] • [Zhang, Liu, Li and Yum, 2005] • [Zhou, Liu, 2005] • [Chi, Zhang, Packet Video 2006]

  31. Downlink Uplink Percentage 512 kb/s 256 kb/s 56% 3 Mb/s 384 kb/s 21% 1.5 Mb/s 896 kb/s 9% 20 Mb/s 2 Mb/s 3% 20 Mb/s 5 Mb/s 11% Experimental Setup • Network/protocol simulation in ns-2 • 300 active peers • Random peer arrival/departure average life-time 5 minutes • Over-provisioned backbone • Typical access rate distribution • Delay: 5 ms/link + congestion • Video streaming • H.264/AVC encoder @ 250 kb/s • 15 minute live multicast [Sripanidkulchai et al.,2004] [Setton, Noh, Girod, 2005]

  32. Join and Rejoin Latencies Simulations over ns-2, 300 peers Number of trees: 4 Retransmissions enabled [Setton, Noh, Girod, 2005]

  33. P2P Video Multicast: 64 out of 300 Peers CoDiO retransmissions No retransmissions H.264 @ 250 kb/s2 second playout deadline for all streams

  34. P2P Video Multicast: 64 out of 300 Peers CoDiO retransmissions No retransmissions H.264 @ 250 kb/s2 second playout deadline for all streams

  35. CoDiO Scheduling for Multicast Trees Child Parent I B P P P B B Child DI DP3 DB DB DP2 DP1 DB [Setton, Noh, Girod, 2006]

  36. Gain by Multicast CoDiO Foreman Mother & Daughter 30 % 40 % Playout deadline (s) Playout deadline (s) Simulations over ns-2, 300 peers Number of trees: 4 Retransmissions enabled [Setton, Noh, Girod, 2006]

  37. Average Video Sequence for 75 Peers Sender-driven CoDiO light 33.71 dB Without prioritization 30.17 dB H.264 @ 250 kb/s0.8 second playout deadline for all streams

  38. Conclusions • Must avoid congestion for low latency • Video streaming over bottlenecks (IPTV, WLAN . . . ):combine admission control and rate control • R-D-aware rate allocation better than fair sharing • Packet scheduling should consider congestion rather than rate • Low-complexity CoDiO scheduler • P2P video multicast possible with low latency • Retransmissions effective with application-layer multicast • CoDiO extended to packet scheduling for multicast trees Cross-layer paradigm Media-aware transport  superior system performance

  39. The End http://www.stanford.edu/~bgirod/publications.html