期刊文献+

基于内容流行度差异性的CDN-P2P融合分发网络缓存替换机制研究 被引量:9

Content popularity difference-aware cache eviction scheme for CDN-P2P hybrid networks
下载PDF
导出
摘要 现有的CDN-P2P缓存替换机制没有关注内容文件中各片段的个体流行度差异性,而无法提高预缓存内容片段的访问命中率。鉴于此,提出了基于流行度差异性的缓存替换机制Diff-Attribute。同时考虑了内容文件的整体流行度和文件中各个片段的个体流行度。此外,基于分布熵,定义了一种内容流行度均衡性度量方法:若流行度均衡,就提前缓存各文件的前缀片段;否则提前缓存热门文件或其中最热门的内容片段。仿真结果表明:在缓存命中率和字节命中率方面,Diff-Attribute机制分别高出LFU、LRU等传统机制约6%和8%;在访问延迟启动率和传输成本消耗率方面,Diff-Attribute机制则降低了约13%和7%。 In CDN-P2 P hybrid network, it is important for the cache eviction schemes to improve the delivery efficiency of content. However, most of them only consider the holistic popularity of content file, and neglect the difference between the individual popularities of segments within a content file. Hence, it was difficult to improve the hit rate of pre-cached content segments, and to reduce the user access delay. Hence based on the difference between the attributes of content popularity, a new cache eviction scheme(i.e., Diff-Attribute) was proposed. Bewildered the holistic popularity of a content file, it also considered the individual popularity of its segment. More importantly, based on the concept of entropy, A method to measure the popularity difference between content files or segments was put forward. If the popularities of the segments within a content file are equalizing, its prefix segment would be pre-cached. Otherwise, the requested segments or files directly based on its popularity would be cached. Compared with traditional schemes(e.g., LFU, LRU, MRU,FIFO), the simulation results show that Diff-Attribute can improve the cache hit rate and the byte hit rate by at least 6%, 8% respectively, and can reduce the access startup delay rate and the transmission cost rate by at least 13%, 7% respectively.
出处 《通信学报》 EI CSCD 北大核心 2015年第S1期9-15,共7页 Journal on Communications
基金 国家自然科学基金资助项目(61172048 61100184)~~
关键词 内容分发网络 内容缓存 P2P网络 流行度 分布熵 content distribution network cache eviction peer-to-peer network(P2P) content popularity entropy
  • 相关文献

参考文献15

  • 1WU T,KOEN D,WERNER V.Reuse time based caching policy for video streaming. Proceedings of the 9th Annual IEEE Consumer Communications and Networking Conference-Multimedia&Entertainment Networking and Services . 2012
  • 2LIU Y,LI F,GUO L.A server’’s perspective of internet streaming delivery to mobile devices. Proceedings of the 24th IEEE INFOCOM . 2012
  • 3G. Carofiglio,G. Morabito,L. Muscariello,I. Solis,M. Varvello.??From Content Delivery Today to Information Centric Networking(J)Computer Networks . 2013
  • 4Nan Zhang,Tapio Lev?,Heikki H?mm?inen.??Value networks and two-sided markets of Internet content delivery(J)Telecommunications Policy . 2013
  • 5Jeroen Famaey,Frédéric Iterbeke,Tim Wauters,Filip De Turck.??Towards a predictive cache replacement strategy for multimedia content(J)Journal of Network and Computer Applications . 2013 (1)
  • 6Jun-Li Kuo,Chen-Hua Shih,Cheng-Yuan Ho,Yaw-Chung Chen.??A cross-layer approach for real-time multimedia streaming on wireless peer-to-peer ad hoc network(J)Ad Hoc Networks . 2013 (1)
  • 7Study uncovers critical link between video quality and audience retention,revenue opportunities. http://www.akamai.com/ . 2013
  • 8ACM SIGMETRICS/Performance 2012 12th Joint International Conference on Measurement and Modeling of Computer Systems (GBR London 2012 06 11 - 2012 06 15),Gallo M.,Kauffmann B.,Muscariello L.,Simonian A.,Tanguy C.Performance evaluation of the random replacement policy for networks of caches. Performance Evaluation . 2012
  • 9Joonho Choi,Abu (Sayeem) Reaz,Biswanath Mukherjee.A Survey of User Behavior in VoD Service and Bandwidth-Saving Multicast Streaming Schemes. IEEE COMMUNICATIONS SURVEYS AND TUTORIALS . 2012
  • 10Chourouk Hammami,Imen Jemili,Achraf Gazdar,Abdelfettah Belghith,Mohamed Mosbah.??Hybrid Live P2P Streaming Protocol(J)Procedia Computer Science . 2014

二级参考文献9

  • 1肖明忠,李晓明,刘翰宇,代亚非,张进宇.基于流媒体文件字节有用性的代理服务器缓存替代策略[J].计算机学报,2004,27(12):1633-1641. 被引量:17
  • 2ROBINSON J T, DEVARAKONDA M V. Data cache management using frequency-based replacement[A]. Proceedings of SIGMETRIC on Measuring and Modeling of Computer Systems[C]. Boulder, Colorado, USA, 1990. 134-142.
  • 3ALGHAZO J, AKAABOUNE A, BOTROS N. SF-LRU Cache RePlacement Algorithm[R]. Records of The 2004 International Workshopon 9-10. 2004. 19 -24.
  • 4SEUNG W S, KI Y K, JONG S J. LRU based small latency first replacement (SLFR) algorithm for the proxy cache[A]. Proceedings of IEEE International Conference on Web Intelligence[C]. 2003. 499-502.
  • 5CHEN S Q, SHEN B, WEE S, et al. Adaptive and lazy segmentation based proxy caching for streaming media delivery[A]. Proceedings of the 13th International Workshop on Network and Operating Systems Support for Digital Audio and Video[C]. 2003.22-31.
  • 6WU K L, YU P S, WOLF J L. Segmentation of multimodia streams for proxy caching[J].IEEE Transactions on Multimedia, 2004,6(5): 770- 780.
  • 7CHESIRE M, WOLMAN A, VOELKER G M, et al. Measurement and analysis of a streaming media workload[A]. Proceedings of the Third USENIX Symposium on Internet Technologies and Systems(USITS-01)[C]. 2001.1-12.
  • 8WANG B, SEN S, ADLER M, et al. Optimal proxy cache allocation for efficient streaming media distribution[A]. Proceedings of IEEE INFOCOM 2002[C]. New York, 2002.1726-1735.
  • 9YANG B, LIAO J X, ZHU X M. Two-level proxy: the media streaming cache architecture for GPRS mobile network[A]. The International Conference on Information Networking 2006[C]. Sendai, Japan,2006.16-19.

共引文献7

同被引文献34

引证文献9

二级引证文献12

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部