Is random scheduling sufficient in P2P video streaming?

Chao Liang, Yang Guo, Yong Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Peer-to-Peer (P2P) technology has recently been employed to deliver large scale video multicast services on the Internet. Considerable efforts have been made by both academia and industry on P2P streaming design. While academia mostly focus on exploring design space to approach the theoretical performance bounds, our recent measurement study on several commercial P2P streaming systems indicates that they are able to deliver good user Quality of Experience with seemingly simple designs. One intriguing question remains: how elaborate should a good P2P video streaming design be? Towards answering this question, we developed and implemented several representative P2P streaming designs, ranging from theoretically proved optimal designs to straightforward "naive" designs. Through an extensive comparison study on PlanetLab, we unveil several key factors contributing to the successes of simple P2P streaming designs, including system resource index, sever capacity and chunk scheduling rule, peer download buffering and peering degree. We also identify regions where naive designs are inadequate and more elaborate designs can improve things considerably. Our study not only brings us better understandings and more insights into the operation of existing systems, it also sheds lights on the design of future systems that can achieve a good balance between the performance and the complexity.

Original languageEnglish (US)
Title of host publicationProceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008
Pages53-60
Number of pages8
DOIs
StatePublished - 2008
Event28th International Conference on Distributed Computing Systems, ICDCS 2008 - Beijing, China
Duration: Jul 17 2008Jul 20 2008

Other

Other28th International Conference on Distributed Computing Systems, ICDCS 2008
CountryChina
CityBeijing
Period7/17/087/20/08

Fingerprint

Video streaming
Scheduling
Internet

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Liang, C., Guo, Y., & Liu, Y. (2008). Is random scheduling sufficient in P2P video streaming? In Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008 (pp. 53-60). [4595868] https://doi.org/10.1109/ICDCS.2008.103

Is random scheduling sufficient in P2P video streaming? / Liang, Chao; Guo, Yang; Liu, Yong.

Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008. 2008. p. 53-60 4595868.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liang, C, Guo, Y & Liu, Y 2008, Is random scheduling sufficient in P2P video streaming? in Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008., 4595868, pp. 53-60, 28th International Conference on Distributed Computing Systems, ICDCS 2008, Beijing, China, 7/17/08. https://doi.org/10.1109/ICDCS.2008.103
Liang C, Guo Y, Liu Y. Is random scheduling sufficient in P2P video streaming? In Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008. 2008. p. 53-60. 4595868 https://doi.org/10.1109/ICDCS.2008.103
Liang, Chao ; Guo, Yang ; Liu, Yong. / Is random scheduling sufficient in P2P video streaming?. Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008. 2008. pp. 53-60
@inproceedings{8b9f10c9bc64403d9cfd90388a5a587f,
title = "Is random scheduling sufficient in P2P video streaming?",
abstract = "Peer-to-Peer (P2P) technology has recently been employed to deliver large scale video multicast services on the Internet. Considerable efforts have been made by both academia and industry on P2P streaming design. While academia mostly focus on exploring design space to approach the theoretical performance bounds, our recent measurement study on several commercial P2P streaming systems indicates that they are able to deliver good user Quality of Experience with seemingly simple designs. One intriguing question remains: how elaborate should a good P2P video streaming design be? Towards answering this question, we developed and implemented several representative P2P streaming designs, ranging from theoretically proved optimal designs to straightforward {"}naive{"} designs. Through an extensive comparison study on PlanetLab, we unveil several key factors contributing to the successes of simple P2P streaming designs, including system resource index, sever capacity and chunk scheduling rule, peer download buffering and peering degree. We also identify regions where naive designs are inadequate and more elaborate designs can improve things considerably. Our study not only brings us better understandings and more insights into the operation of existing systems, it also sheds lights on the design of future systems that can achieve a good balance between the performance and the complexity.",
author = "Chao Liang and Yang Guo and Yong Liu",
year = "2008",
doi = "10.1109/ICDCS.2008.103",
language = "English (US)",
isbn = "9780769531724",
pages = "53--60",
booktitle = "Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008",

}

TY - GEN

T1 - Is random scheduling sufficient in P2P video streaming?

AU - Liang, Chao

AU - Guo, Yang

AU - Liu, Yong

PY - 2008

Y1 - 2008

N2 - Peer-to-Peer (P2P) technology has recently been employed to deliver large scale video multicast services on the Internet. Considerable efforts have been made by both academia and industry on P2P streaming design. While academia mostly focus on exploring design space to approach the theoretical performance bounds, our recent measurement study on several commercial P2P streaming systems indicates that they are able to deliver good user Quality of Experience with seemingly simple designs. One intriguing question remains: how elaborate should a good P2P video streaming design be? Towards answering this question, we developed and implemented several representative P2P streaming designs, ranging from theoretically proved optimal designs to straightforward "naive" designs. Through an extensive comparison study on PlanetLab, we unveil several key factors contributing to the successes of simple P2P streaming designs, including system resource index, sever capacity and chunk scheduling rule, peer download buffering and peering degree. We also identify regions where naive designs are inadequate and more elaborate designs can improve things considerably. Our study not only brings us better understandings and more insights into the operation of existing systems, it also sheds lights on the design of future systems that can achieve a good balance between the performance and the complexity.

AB - Peer-to-Peer (P2P) technology has recently been employed to deliver large scale video multicast services on the Internet. Considerable efforts have been made by both academia and industry on P2P streaming design. While academia mostly focus on exploring design space to approach the theoretical performance bounds, our recent measurement study on several commercial P2P streaming systems indicates that they are able to deliver good user Quality of Experience with seemingly simple designs. One intriguing question remains: how elaborate should a good P2P video streaming design be? Towards answering this question, we developed and implemented several representative P2P streaming designs, ranging from theoretically proved optimal designs to straightforward "naive" designs. Through an extensive comparison study on PlanetLab, we unveil several key factors contributing to the successes of simple P2P streaming designs, including system resource index, sever capacity and chunk scheduling rule, peer download buffering and peering degree. We also identify regions where naive designs are inadequate and more elaborate designs can improve things considerably. Our study not only brings us better understandings and more insights into the operation of existing systems, it also sheds lights on the design of future systems that can achieve a good balance between the performance and the complexity.

UR - http://www.scopus.com/inward/record.url?scp=51849100253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51849100253&partnerID=8YFLogxK

U2 - 10.1109/ICDCS.2008.103

DO - 10.1109/ICDCS.2008.103

M3 - Conference contribution

SN - 9780769531724

SP - 53

EP - 60

BT - Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008

ER -