对等流媒体点播系统主动复制机制的研究
|
摘要
对等点播技术已成功运用于越来越多的大规模商业视频点播系统,其客户端数据缓存和共享的特点降低了源服务器的带宽负载。但是,对等网络具有与生俱来的动态特性,节点的频繁退出使大量已缓存数据处于离线状态,无法与其它用户共享。这极大降低了客户端缓存资源的利用程度,将原本可由客户端所承担的带宽压力转移到数据源服务器,导致对等点播系统服务器带宽负载不能充分改善。
对等点播系统主动复制机制iDARE(Proactive Data Replication Mechanism)有效解决了上述问题。iDARE机制通过数据复制的方式延长将要离线节点上缓存数据的生命周期,提高其被继续共享的可能性。iDARE机制在传统的对等点播系统中引入数据缓存层,由中央管理节点和分布式缓存服务器组成,处于不稳定状态的节点主动复制所缓存的视频数据到稳定可靠的缓存层存储资源。根据已部署对等点播系统中用户动态行为的分析,iDARE机制提出两个核心算法,一个是基于节点在线时长和播放位置的复制时机确定算法,决定用户何时启动数据复制流程。另一个是基于数据块复制价值的上传数据选择算法,保证用户选择的是近期最有可能被大量请求但副本缓存数量较少的数据块。iDARE机制正常运转的核心功能包括用户节点数据供需基本信息的收集,频道数据块复制价值的计算,分布式缓存服务器的任务调度,以及基于多频道缓存的数据上传和基于缓存服务器的数据调度。
系统测试与仿真结果表明,iDARE机制有效提高了用户数据请求在缓存服务器的命中率,与原对等网络点播系统相比,源服务器带宽负载降低了约40%。同时,性能对比表明iDARE机制提出的复制数据选择算法,相比随机和基于流行度的数据选择算法,缓存层命中率分别由4.5%和13.2%升至26.4%。iDARE提出的复制时机确定算法,在同等性能表现下,所消耗的总用户上行流量仅为贪婪算法的约四分之一。
P2P (Peer-to-Peer) technology has been successfully applied to more and more large scale commercial VoD (Video-on-Demand) streaming systems, due to its excellent characteristic that the client-side data caching and sharing of P2P could dramatically reduce the source server loading. However, frequent peers departure caused by the intrinsic dynamics under P2P overlay network makes a great number of cached media data become offline and unavailable to other peers. This problem greatly decreases the utilization efficiency of client-side cache resources, and transfers the bandwidth burden expected for overlay peers to source server, which causes that the server’s bandwidth cost could not be fully improved.
iDARE (Proactive Data Replication Mechanism) employs replication to increase the lifetime of high utility media data on to-be-offline peers, which improves the possibility for further sharing these data. Compared to traditional pure P2P VoD architecture, iDARE introduces the data caching layer that composed of a central managing node and distributed cache servers, for stable and reliable storage of replicated media data from peers. After careful analysis on peer churn of a currently deployed P2P VoD service named GridCast, iDARE implemented two core algorithms. One algorithm is used for determining when to trigger peer’s proactive data replication procedure, and the decision making is based on both peer uptime length and current playback position. The other one guides peers through the selection of to-be-uploaded media data by evaluating the replication value of each cached chunks, which prioritizes data chunks that have high demand but rarely cached on peers. The core functionalities that assure the regular operation of iDARE include centralized clustering of media supply-demand information from peers, calculation of video channel’s replication value, task scheduling of the distributed cache servers, data upload based on MVC (Multiple Video Caching) and data scheduling based on cache server.
Our evaluation and simulation demonstrate that GridCast incorporated with iDARE mechanism could effectively improve the hit rate of cache servers and decrease the source server loading by 40% compared with previous pure P2P architecture only contributed by peers. In addition, after employing new replicate chunks selection algorithms of iDARE, the caching layer hit rate has increased from in average 4.5% of random algorithm and 13.2% of popularity-based algorithm to 26.4%. And the proposed algorithm for determining replication opportunity has excellent performance at the low cost of only one fourth of the total upload network traffic using eager algorithm.
对等点播系统主动复制机制iDARE(Proactive Data Replication Mechanism)有效解决了上述问题。iDARE机制通过数据复制的方式延长将要离线节点上缓存数据的生命周期,提高其被继续共享的可能性。iDARE机制在传统的对等点播系统中引入数据缓存层,由中央管理节点和分布式缓存服务器组成,处于不稳定状态的节点主动复制所缓存的视频数据到稳定可靠的缓存层存储资源。根据已部署对等点播系统中用户动态行为的分析,iDARE机制提出两个核心算法,一个是基于节点在线时长和播放位置的复制时机确定算法,决定用户何时启动数据复制流程。另一个是基于数据块复制价值的上传数据选择算法,保证用户选择的是近期最有可能被大量请求但副本缓存数量较少的数据块。iDARE机制正常运转的核心功能包括用户节点数据供需基本信息的收集,频道数据块复制价值的计算,分布式缓存服务器的任务调度,以及基于多频道缓存的数据上传和基于缓存服务器的数据调度。
系统测试与仿真结果表明,iDARE机制有效提高了用户数据请求在缓存服务器的命中率,与原对等网络点播系统相比,源服务器带宽负载降低了约40%。同时,性能对比表明iDARE机制提出的复制数据选择算法,相比随机和基于流行度的数据选择算法,缓存层命中率分别由4.5%和13.2%升至26.4%。iDARE提出的复制时机确定算法,在同等性能表现下,所消耗的总用户上行流量仅为贪婪算法的约四分之一。
P2P (Peer-to-Peer) technology has been successfully applied to more and more large scale commercial VoD (Video-on-Demand) streaming systems, due to its excellent characteristic that the client-side data caching and sharing of P2P could dramatically reduce the source server loading. However, frequent peers departure caused by the intrinsic dynamics under P2P overlay network makes a great number of cached media data become offline and unavailable to other peers. This problem greatly decreases the utilization efficiency of client-side cache resources, and transfers the bandwidth burden expected for overlay peers to source server, which causes that the server’s bandwidth cost could not be fully improved.
iDARE (Proactive Data Replication Mechanism) employs replication to increase the lifetime of high utility media data on to-be-offline peers, which improves the possibility for further sharing these data. Compared to traditional pure P2P VoD architecture, iDARE introduces the data caching layer that composed of a central managing node and distributed cache servers, for stable and reliable storage of replicated media data from peers. After careful analysis on peer churn of a currently deployed P2P VoD service named GridCast, iDARE implemented two core algorithms. One algorithm is used for determining when to trigger peer’s proactive data replication procedure, and the decision making is based on both peer uptime length and current playback position. The other one guides peers through the selection of to-be-uploaded media data by evaluating the replication value of each cached chunks, which prioritizes data chunks that have high demand but rarely cached on peers. The core functionalities that assure the regular operation of iDARE include centralized clustering of media supply-demand information from peers, calculation of video channel’s replication value, task scheduling of the distributed cache servers, data upload based on MVC (Multiple Video Caching) and data scheduling based on cache server.
Our evaluation and simulation demonstrate that GridCast incorporated with iDARE mechanism could effectively improve the hit rate of cache servers and decrease the source server loading by 40% compared with previous pure P2P architecture only contributed by peers. In addition, after employing new replicate chunks selection algorithms of iDARE, the caching layer hit rate has increased from in average 4.5% of random algorithm and 13.2% of popularity-based algorithm to 26.4%. And the proposed algorithm for determining replication opportunity has excellent performance at the low cost of only one fourth of the total upload network traffic using eager algorithm.
引文
[1] Apostolopoulos J, Tan W, Wee S. Video streaming: Concepts, Algorithms, and Systems. http: //www. hpl. hp. com/techreports/2002/HPL-2002-260. pdf
[2] Cha M, Kwak H, Rodriguez P et al. I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system. In Proceedings of the 7th ACM SIGCOMM Conference on internet Measurement (IMC’07). San Diego, California, USA, October 24-26, 2007. New York, NY: ACM Press. 1~14
[3]王福臣,金海,程斌等.一种P2P点播系统中的数据调度策略.华中科技大学学报(自然科学版), 2006, 34(I): 152~155
[4] YouTube Website. Available: http: //www. youtube. com
[5]李璠. P2P技术在IPTV中的应用.微机计算机信息, 2007 23(12): 28~30
[6] Huang C, Li J, Ross K W. Can internet video-on-demand be profitable? In Proceedings of the 2007 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM’07). Kyoto, Japan, August 27-31, 2007. New York, NY: ACM Press. 133~144
[7] Huang C, Li J, Ross K W. Peer-Assisted VoD: Making Internet Video Distribution Cheap. In Proceedings of IPTPS’07. Bellevue, WA, USA, Feb. 2007
[8] Guo Y, Suh K, Kurose J et al. P2Cast: peer-to-peer patching scheme for VoD service. In Proceedings of the 12th international Conference on World Wide Web (WWW’03). Budapest, Hungary, May 20-24, 2003. New York, NY: ACM Press. 301~309
[9] Joost Website. Available: http: //www. joost. com
[10] PPStream Website. Available: http: //www. ppstream. com
[11] Janardhan V, Schulzrinne H. Peer assisted VoD for set-top box based IP network. In Proceedings of the 2007 Workshop on Peer-To-Peer Streaming and IP-TV (PTP-TV’07). Kyoto, Japan, August 27-31, 2007. New York, NY: ACM Press. 335~339
[12] Ripeanu M, Iamnitchi A, Foster I. Mapping the Gnutella Network. IEEE InternetComputing, 2007, 6, 1: 50~5
[13] Maymounkov P, Mazieres D. Kademlia: A Peer-to-Peer Information System Based on the XOR Metric. In Proceedings of IPTPS’2002. Cambridge, MA, USA, Mar. 2002
[14] Cohen B. Incentives build robustness in BitTorrent. In Proceedings of the 1st Workshop on Economics of Peer-to-Peer Systems, 2003
[15] Stutzbach D, Rejaie R. Understanding churns in peer-to-peer networks. In Proceedings of the 6th ACM SIGCOMM Conference on internet Measurement (IMC’06). Rio de Janeriro, Brazil, October 25-27, 2006. New York, NY: ACM Press. 189~202
[16] Tian J, Dai Y. Understanding the Dynamic of Peer-to-Peer Systems. In Proceedings of IPTPS’07. Bellevue, WA, USA, Feb. 2007.
[17] Leibowitz N, Ripeanu M, Wierzbicki. Deconstructing the Kazaa Network. In Proceedings of the the Third IEEE Workshop on internet Applications (WIAPP’03). San Jose, CA, USA, June 23-24, 2003. Washington, DC, USA: IEEE Computer Society. 112
[18] Bustamante F E, Qiao Y. Friendships that last: Peer lifespan and its role in P2P protocols. In Proceedings of the 8th International Workshop on Web Content Caching and Distribution (IWCW’03). Hawthorne, NY, USA, Sep. 29-Oct. 1, 2003. Netherlands: Springer. 233~246
[19] Bhagwan R, Savage S, Voelker G. Understanding Availability. In Proceedings of IPTPS'03. Berkeley, CA, USA, Feb. 2003
[20] Mickens J W, Noble B D. Exploiting availability prediction in distributed systems. In Proceedings of the 3rd Conference on Networked Systems Design & Implementation-Volume 3 (NSDI’06). San Jose, CA, May 08-10, 2006. Berkeley, CA: USENIX Association. 6~6
[21] Cherkasova L, Gupta M. Characterizing locality, evolution, and life span of accesses in enterprise media server workloads. In Proceedings of the 12th international Workshop on Network and Operating Systems Support For Digital Audio and Video (NOSSDAV '02). Miami, Florida, USA, May 12-14, 2002. New York, NY: ACM Press. 33~42
[22] Yu H, Zheng D, Zhao B Y et al. Understanding user behavior in large-scale video-on-demand systems. In Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems 2006 (Eurosys’06). Leuven, Belgium, April 18-21, 2006. New York, NY: ACM Press. 333~344
[23] Guo L, Tan E, Chen S et al. The stretched exponential distribution of internet media access patterns. In Proceedings of the Twenty-Seventh ACM Symposium on Principles of Distributed Computing (PODC’08). Toronto, Canada, August 18-21, 2008. New York, NY: ACM Press. 283~294
[24] Gopalakrishnan V, Silaghi B, Bhattacharjee B et al. Adaptive Replication in Peer-to-Peer Systems. In Proceedings of the 24th international Conference on Distributed Computing Systems (ICDCS’04). Tokyo, Japan, March 24-26, 2004. Washington, DC: IEEE Computer Society. 360~369
[25] Cohen E, Shenker S. Replication strategies in unstructured peer-to-peer networks. In Proceedings of the 2002 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM’02). Pittsburgh, Pennsylvania, USA, August 19-23, 2002. New York, NY: ACM Press. 177~190
[26] Kangasharju J, Roberts J, Ross K W. Object replication strategies in content distribution networks. Computer Communications, 1 March 2002, Volume 25, Issue 4: 376~383
[27] Yan C, Katz R H, Kubiatowicz J. Dynamic Replica Placement for Scalable Content Delivery. In Proceedings of IPTPS’2002. Cambridge, MA, USA, Mar. 2002.
[28] Bhagwan R, Tati K, Cheng Y et al. Total recall: system support for automated availability management. In Proceedings of the 1st Conference on Symposium on Networked Systems Design and Implementation-Volume 1(NSDI'04). San Francisco, CA, USA, March 29–31. Berkeley, CA: USENIX Association. 25~25
[29] Ranganathan K, Iamnitchi A, Foster I. Improving Data Availability through Dynamic Model-Driven Replication in Large Peer-to-Peer Communities. In Proceedings of the 2nd IEEE/ACM international Symposium on Cluster Computing and the Grid (CCGRID’02). Berlin, Germany, May 21-24, 2002. Washington, DC: IEEE Computer Society. 376
[30] Ditze M, Loeser C, Altenbernd P et al. Improving Content Replication and QoS inDistributed Peer-to-Peer Appliances. In Proceedings of the 24th international Conference on Distributed Computing Systems Workshops - W7: EC - Volume 7 (ICDCSW’04). Tokyo, Japan, March 24-26, 2004. Washington, DC: IEEE Computer Society. 78~84
[31] Wan K H, Loeser C. An overlay network for replica placement within a P2P VoD network. International Journal on High Performance Computing and Networking, Dec. 2005, Volume 3, Issue 5/6: 320~335
[32] Vratonjic N, Gupta P, Knezevic N et al. Enabling DVD-like features in P2P video-on-demand systems. In Proceedings of the 2007 Workshop on Peer-To-Peer Streaming and IP-TV (P2P-TV’07). Kyoto, Japan, August 27-31, 2007. New York, NY: ACM Press. 329~334
[33] Cheng B, Stein L, Jin H et al. A framework for lazy replication in P2P VoD. In Proceedings of the 18th international Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV '08). Braunschweig, Germany, May 28-30, 2008. New York, NY: ACM Press. 93~98
[34] Huang Y, Fu T Z, Chiu D et al. Challenges, design and analysis of a large-scale p2p-vod system. In Proceedings of the ACM SIGCOMM 2008 Conference on Data Communication (SIGCOMM '08). Seattle, WA, USA, August 17-22, 2008. New York, NY: ACM Press. 375~388
[35] Guo L, Chen S, Ren S et al. PROP: A Scalable and Reliable P2P Assisted Proxy Streaming System. In Proceedings of the 24th international Conference on Distributed Computing Systems (ICDCS'04). Tokyo, Japan, March 24-26, 2004. Washington, DC: IEEE Computer Society. 778~786
[36] Dan G. Cooperative caching and relaying strategies for peer-to-peer content delivery. In Proceedings of IPTPS'08. Tampa, FL, USA, Feb. 2008.
[37] Alan T S, Liu J C, Lui J C. COPACC: An Architecture of Cooperative Proxy-Client Caching System for On-Demand Media Streaming. IEEE Transactions on Parallel and Distributed Systems (TPDS), Jan. 2007, v. 18 n. 1: 70~83
[38] Cheng B, Stein L, Jin H et al. GridCast: Improving peer sharing for P2P VoD. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), Oct. 2008, v. 4 n. 4: 1~31
[39] Cheng B, Stein L, Jin H et al. Towards cinematic internet video-on-demand. In Proceedings of the 3rd ACM SIGOPS/EuroSys European Conference on Computer Systems 2008 (Eurosys'08). Glasgow, Scotland UK, April 01-04, 2008. New York, NY: ACM Press. 109~122
[40] Cheng B, Liu X, Zhang Z et al. A Measurement Study of a Peer-to-Peer Video-on-Demand System. In Proceedings of IPTPS’07. Bellevue, WA, USA, Feb. 2007
[2] Cha M, Kwak H, Rodriguez P et al. I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system. In Proceedings of the 7th ACM SIGCOMM Conference on internet Measurement (IMC’07). San Diego, California, USA, October 24-26, 2007. New York, NY: ACM Press. 1~14
[3]王福臣,金海,程斌等.一种P2P点播系统中的数据调度策略.华中科技大学学报(自然科学版), 2006, 34(I): 152~155
[4] YouTube Website. Available: http: //www. youtube. com
[5]李璠. P2P技术在IPTV中的应用.微机计算机信息, 2007 23(12): 28~30
[6] Huang C, Li J, Ross K W. Can internet video-on-demand be profitable? In Proceedings of the 2007 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM’07). Kyoto, Japan, August 27-31, 2007. New York, NY: ACM Press. 133~144
[7] Huang C, Li J, Ross K W. Peer-Assisted VoD: Making Internet Video Distribution Cheap. In Proceedings of IPTPS’07. Bellevue, WA, USA, Feb. 2007
[8] Guo Y, Suh K, Kurose J et al. P2Cast: peer-to-peer patching scheme for VoD service. In Proceedings of the 12th international Conference on World Wide Web (WWW’03). Budapest, Hungary, May 20-24, 2003. New York, NY: ACM Press. 301~309
[9] Joost Website. Available: http: //www. joost. com
[10] PPStream Website. Available: http: //www. ppstream. com
[11] Janardhan V, Schulzrinne H. Peer assisted VoD for set-top box based IP network. In Proceedings of the 2007 Workshop on Peer-To-Peer Streaming and IP-TV (PTP-TV’07). Kyoto, Japan, August 27-31, 2007. New York, NY: ACM Press. 335~339
[12] Ripeanu M, Iamnitchi A, Foster I. Mapping the Gnutella Network. IEEE InternetComputing, 2007, 6, 1: 50~5
[13] Maymounkov P, Mazieres D. Kademlia: A Peer-to-Peer Information System Based on the XOR Metric. In Proceedings of IPTPS’2002. Cambridge, MA, USA, Mar. 2002
[14] Cohen B. Incentives build robustness in BitTorrent. In Proceedings of the 1st Workshop on Economics of Peer-to-Peer Systems, 2003
[15] Stutzbach D, Rejaie R. Understanding churns in peer-to-peer networks. In Proceedings of the 6th ACM SIGCOMM Conference on internet Measurement (IMC’06). Rio de Janeriro, Brazil, October 25-27, 2006. New York, NY: ACM Press. 189~202
[16] Tian J, Dai Y. Understanding the Dynamic of Peer-to-Peer Systems. In Proceedings of IPTPS’07. Bellevue, WA, USA, Feb. 2007.
[17] Leibowitz N, Ripeanu M, Wierzbicki. Deconstructing the Kazaa Network. In Proceedings of the the Third IEEE Workshop on internet Applications (WIAPP’03). San Jose, CA, USA, June 23-24, 2003. Washington, DC, USA: IEEE Computer Society. 112
[18] Bustamante F E, Qiao Y. Friendships that last: Peer lifespan and its role in P2P protocols. In Proceedings of the 8th International Workshop on Web Content Caching and Distribution (IWCW’03). Hawthorne, NY, USA, Sep. 29-Oct. 1, 2003. Netherlands: Springer. 233~246
[19] Bhagwan R, Savage S, Voelker G. Understanding Availability. In Proceedings of IPTPS'03. Berkeley, CA, USA, Feb. 2003
[20] Mickens J W, Noble B D. Exploiting availability prediction in distributed systems. In Proceedings of the 3rd Conference on Networked Systems Design & Implementation-Volume 3 (NSDI’06). San Jose, CA, May 08-10, 2006. Berkeley, CA: USENIX Association. 6~6
[21] Cherkasova L, Gupta M. Characterizing locality, evolution, and life span of accesses in enterprise media server workloads. In Proceedings of the 12th international Workshop on Network and Operating Systems Support For Digital Audio and Video (NOSSDAV '02). Miami, Florida, USA, May 12-14, 2002. New York, NY: ACM Press. 33~42
[22] Yu H, Zheng D, Zhao B Y et al. Understanding user behavior in large-scale video-on-demand systems. In Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems 2006 (Eurosys’06). Leuven, Belgium, April 18-21, 2006. New York, NY: ACM Press. 333~344
[23] Guo L, Tan E, Chen S et al. The stretched exponential distribution of internet media access patterns. In Proceedings of the Twenty-Seventh ACM Symposium on Principles of Distributed Computing (PODC’08). Toronto, Canada, August 18-21, 2008. New York, NY: ACM Press. 283~294
[24] Gopalakrishnan V, Silaghi B, Bhattacharjee B et al. Adaptive Replication in Peer-to-Peer Systems. In Proceedings of the 24th international Conference on Distributed Computing Systems (ICDCS’04). Tokyo, Japan, March 24-26, 2004. Washington, DC: IEEE Computer Society. 360~369
[25] Cohen E, Shenker S. Replication strategies in unstructured peer-to-peer networks. In Proceedings of the 2002 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM’02). Pittsburgh, Pennsylvania, USA, August 19-23, 2002. New York, NY: ACM Press. 177~190
[26] Kangasharju J, Roberts J, Ross K W. Object replication strategies in content distribution networks. Computer Communications, 1 March 2002, Volume 25, Issue 4: 376~383
[27] Yan C, Katz R H, Kubiatowicz J. Dynamic Replica Placement for Scalable Content Delivery. In Proceedings of IPTPS’2002. Cambridge, MA, USA, Mar. 2002.
[28] Bhagwan R, Tati K, Cheng Y et al. Total recall: system support for automated availability management. In Proceedings of the 1st Conference on Symposium on Networked Systems Design and Implementation-Volume 1(NSDI'04). San Francisco, CA, USA, March 29–31. Berkeley, CA: USENIX Association. 25~25
[29] Ranganathan K, Iamnitchi A, Foster I. Improving Data Availability through Dynamic Model-Driven Replication in Large Peer-to-Peer Communities. In Proceedings of the 2nd IEEE/ACM international Symposium on Cluster Computing and the Grid (CCGRID’02). Berlin, Germany, May 21-24, 2002. Washington, DC: IEEE Computer Society. 376
[30] Ditze M, Loeser C, Altenbernd P et al. Improving Content Replication and QoS inDistributed Peer-to-Peer Appliances. In Proceedings of the 24th international Conference on Distributed Computing Systems Workshops - W7: EC - Volume 7 (ICDCSW’04). Tokyo, Japan, March 24-26, 2004. Washington, DC: IEEE Computer Society. 78~84
[31] Wan K H, Loeser C. An overlay network for replica placement within a P2P VoD network. International Journal on High Performance Computing and Networking, Dec. 2005, Volume 3, Issue 5/6: 320~335
[32] Vratonjic N, Gupta P, Knezevic N et al. Enabling DVD-like features in P2P video-on-demand systems. In Proceedings of the 2007 Workshop on Peer-To-Peer Streaming and IP-TV (P2P-TV’07). Kyoto, Japan, August 27-31, 2007. New York, NY: ACM Press. 329~334
[33] Cheng B, Stein L, Jin H et al. A framework for lazy replication in P2P VoD. In Proceedings of the 18th international Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV '08). Braunschweig, Germany, May 28-30, 2008. New York, NY: ACM Press. 93~98
[34] Huang Y, Fu T Z, Chiu D et al. Challenges, design and analysis of a large-scale p2p-vod system. In Proceedings of the ACM SIGCOMM 2008 Conference on Data Communication (SIGCOMM '08). Seattle, WA, USA, August 17-22, 2008. New York, NY: ACM Press. 375~388
[35] Guo L, Chen S, Ren S et al. PROP: A Scalable and Reliable P2P Assisted Proxy Streaming System. In Proceedings of the 24th international Conference on Distributed Computing Systems (ICDCS'04). Tokyo, Japan, March 24-26, 2004. Washington, DC: IEEE Computer Society. 778~786
[36] Dan G. Cooperative caching and relaying strategies for peer-to-peer content delivery. In Proceedings of IPTPS'08. Tampa, FL, USA, Feb. 2008.
[37] Alan T S, Liu J C, Lui J C. COPACC: An Architecture of Cooperative Proxy-Client Caching System for On-Demand Media Streaming. IEEE Transactions on Parallel and Distributed Systems (TPDS), Jan. 2007, v. 18 n. 1: 70~83
[38] Cheng B, Stein L, Jin H et al. GridCast: Improving peer sharing for P2P VoD. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), Oct. 2008, v. 4 n. 4: 1~31
[39] Cheng B, Stein L, Jin H et al. Towards cinematic internet video-on-demand. In Proceedings of the 3rd ACM SIGOPS/EuroSys European Conference on Computer Systems 2008 (Eurosys'08). Glasgow, Scotland UK, April 01-04, 2008. New York, NY: ACM Press. 109~122
[40] Cheng B, Liu X, Zhang Z et al. A Measurement Study of a Peer-to-Peer Video-on-Demand System. In Proceedings of IPTPS’07. Bellevue, WA, USA, Feb. 2007