一种依赖社会网络的P2P视频点播推荐机制  

Novel Video Recommendation Mechanism for P2P VoD Services

作　　者：和振华[1] 田野[2] 

机构地区：[1]安徽省高性能计算重点实验室,合肥230027 [2]中国科学技术大学计算机科学与技术学院,合肥230026

出　　处：《小型微型计算机系统》2013年第2期229-232,共4页Journal of Chinese Computer Systems

基　　金：安徽省自然科学基金项目(11040606Q52)资助;中央高校基本科研业务专项(WK0110000024)资助

摘　　要：提出一种新颖实用的视频推荐机制,用于缓解高质量P2P视频点播服务中存在的节点带宽饥饿现象.通过分析中国科技大学校园视频点播系统10个月的点播日志,发现视频在视频关联网络有聚簇的趋势,社会网络的现象明显.基于视频的社会网络特性,利用P2P视频点播系统已有的gossip协议,设计了一种新颖实用的基于社会网络的分布式视频推荐机制.利用gossip协议和视频之间的社会网络关系属性,此机制能够分布式的并且低代价的给饥饿节点推荐最优的视频.饥饿的节点通过接受推荐来避免继续陷入饥饿.实验表明该推荐机制能有效地缓解点播节点的带宽饥饿,提高P2P网络资源的利用效率.Abstract ：A practical and novel social network-based video recommendation mechanism is proposed in this paper to alleviate the star- vation in peer-to-peer （ P2P ） video-on-demand （ VoD ） services caused by imbalanced peer bandwidths and high-quality video re- quests. We analyzed log files collected from a campus-wide video-on-demand service of University of Science and Technology of China, and observe that videos requested by users＇tend to cluster together in the network of video association and exhibit strong social network features. We propose a distributed video recommendation mechanism that piggybacks on the gossip protocol of P2P VoD sys- tems. By piggybacking on the gossip protocol and exploiting the social networking property among the videos, the mechanism can recommend videos to starving peers in a distributed and inexpensive way. And by switching to a recommended video, a starving peer can avoid channels that are under starvation. At the same time, the mechanism can effectively enable more successful video requests and alleviate the starvation problem by recommending videos that are not under starvation to interested starving users. Simulation- based experiments show that the mechanism can alleviate the starvation effectively and inexpensively, and improve P2P network＇s re- source utilization.

关 键 词：视频点播 分布式 推荐机制 社会网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]