基于行为特征的超级节点节流算法研究  

Research on algorithm for low bandwidth super-peers network based on user's behavior characteristic

作　　者：何钦[1] 刘丹[1] 周明[1] 

机构地区：[1]电子科技大学电子科学技术研究院,成都611731

出　　处：《计算机工程与应用》2013年第11期61-65,共5页Computer Engineering and Applications

基　　金：宁波市科技局工业;农业与民生领域重大科技攻关项目(No.2011C51007)

摘　　要：针对P2P网络中超级节点失效时带来的资源流失、网络拓扑结构变化和重新选举网络开销增加等问题,提出了一种基于用户行为特征统计的超级节点禅让算法。根据节点的失效统计特征预估失效时间,预先指定继任超级节点。仿真实验对比结果表明,该算法可以有效降低超级节点失效时带来的网络波动,降低网络流量消耗。In a super-peers-based P2P network, if super-peers fail or leave, it may bring many problems, such as resource losing, network topology changing and increasing bandwidth occupancy for re-election. To solve these problem, this paper brings up a super-peers abdicate algorithm based on user＇ s behavior characteristic. According to statistic characteristic of the node failure, the SPAA algorithm can forecast the node leave time and appoint next super-peer. Simulation and analysis show that the SPAA algorithm can effectively reduce the net churn by super-peer failure and reduce network traffic.

关 键 词：超级节点 节点失效 退位算法 降低网络流量 

分 类 号：TP393.0[自动化与计算机技术—计算机应用技术]