分布式VoD系统中一种分层的缓存管理策略  

Cache Management Policy Based on Delamination in Distributed VoD Systems

作　　者：巫旭敏[1] 殷保群[1] 张国荣[1] 胡晗[1] 

机构地区：[1]中国科学技术大学网络传播系统与控制联合实验室网络传播系统与控制安徽省重点实验室,合肥230027

出　　处：《小型微型计算机系统》2013年第7期1548-1553,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61174124;60935001)资助;国家"八六三"高技术研究发展计划项目(2011AA01A107)资助

摘　　要：相对于传统网络服务系统的客户端/服务器构架,分布式VoD系统通过系统中节点间的协作能够获得更好的性能.而节点的存储空间和网络带宽是有限的,因此缓存管理的研究对流媒体服务系统的研发具有重要的意义.该文基于一种灵活的热度估计方法对系统中的存储资源进行分层分析,给出一种减小服务器磁盘I/O负载的优化式及其次优解,同时针对客户节点的不稳定特性提出一种以二次规划为基础的数据置换算法.仿真实验结果表明热度的计算能够较好的反映用户行为的变化,而缓存管理策略有利于减小服务器磁盘数据的读写以及增加系统的可利用资源.In contrast to traditional clients /servers infrastructure,distributed VoD systems have better performance via taking advantage of the cooperation among nodes.Cache management is one of the most important issues in the distributed system because of the limited storage capacity and netw ork bandw idth.In the paper a delamination-based caching policy is analyzed based on the flexible popularity estimate.A formal optimal formula,w hich can reduce disk I / O w ith the caching policy of random access memory,is proposed,and the corresponding suboptimal solution is given.At last a data replace algorithm based on quadratic programming is designed for client nodes w hich are unstable in the netw ork.The simulation results illustrate that clients＇ behavior is tracked better w ith the popularity,the disk I / O is low ered and effectiveness of system cache is boosted by engaging our proposals.

关 键 词：缓存策略 热度估计 视频点播系统 对等网络 内容分发网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]