摘要
P2P系统中节点的动态特性对搜索性能的稳定提出了很大挑战。借鉴社会学和组织学相应原理,提出拓扑演化模型捕获节点的运动规律。节点模拟人类在社会网络中的行为,根据自身和他人的兴趣变化,随搜索过程的进行,利用自身局部信息,动态、自适应地调整网络拓扑,及时反映资源分布以及搜索内容的动态变化,维持资源合理组织。在此基础上提出的智能搜索机制ITSON(InTelligent Search based on tOpologyevolutioN),利用消息转发的智能性进行路由方向决策,从而迅速定位提供资源的节点。仿真结果说明,ITSON能自动优化网络,具有良好的搜索性能和自适应特性。
Efficient search in decentralized peer-to-peer systems is a challenging problem.An intelligent search mechanism based on topology evolution,named ITSON,is proposed.Each peer clustered with peers in similar interests into a community and chose important communities as logical neighbors based on the past queries.For a new arriving query,the most possible communities that have the query answers were selected according to topology evolution to send the query.With queries done,overlay network topology can be adjusted automatically with little cost.Simulations reveal that ITSON greatly improves the search efficiency and guarantees the search effectiveness.
出处
《国防科技大学学报》
EI
CAS
CSCD
北大核心
2010年第5期160-165,共6页
Journal of National University of Defense Technology
基金
国家自然科学基金资助项目(60903225)
国家自然科学基金资助项目(60903206)
关键词
对等网
自组织
拓扑演化
社区
自适应
P2P（Peer to Peer）
self-organization
topology evolution
community
adaptation
