基于幂律分布和小世界特性的无结构P2P网络中搜索方法研究  

Research on Searching in Unstructured P2P Network Based on Power-Law Distribution and Small World Character

作　　者：汤大权[1] 贺明科[1] 孟庆崧[1] 

机构地区：[1]国防科学技术大学信息系统与管理学院,长沙410073

出　　处：《计算机研究与发展》2007年第9期1566-1571,共6页Journal of Computer Research and Development

基　　金：湖南省自然科学基金项目(03JJY3110)

摘　　要：目前无结构P2P系统得到了大量的应用,但其常用的基于简单flooding机制的信息资源搜索方法造成了严重的通信消耗.基于P2P网络的幂律分布和小世界特性,通过对复杂网络幂律特性产生机制的分析并借鉴人际传播中谣言传播机制,提出了一种结合择优连接机制和谣言传播中兴趣衰减机制的信息资源搜索方法.其中择优连接是导致复杂网络幂律特性产生的机制之一,而谣言传播中的兴趣衰减机制适合于聚合网络中的信息传播.分析和仿真结果表明,提出的搜索方法可以有效地减少无结构P2P网络中信息搜索的通信开销.Unstructured peer-to-peer （P2P） systems have been widely used in the Internet. The common search method used is flooding-based broadcasting. This method usually leads to serious communication cost problem. Based on the observation and analysis of social communication network, it is noticed that in social communication network, the transfer of message is optimized. In message spreading, reduplicate communication cost is avoid unwillingly. The rumor spreading mechanism utilizes the clustering characteristic of social communication network in born. The mechanism responsible for the emergence of power-law networks is growth and preferential attachment. In this paper, based on the power-law distribution and small world character of unstructured P2P networks, a search method is presented. This method combines preference link mechanism, which generates the power-law character, and interest decline mechanism in rumor spreading, which is accommodated to clustering network. Mathematical analyses show that this approach could sharply optimize the communication cost in P2P systems. To evaluate the effectiveness of this algorithm, using topology generation tool BRITE to generate simulation network based on the GLP （generalized linear preference） model. The result of the preliminary simulation shows that the communication cost of this algorithm is less than the half of the flooding algorithm, and the overlay degree of this algorithm is quite high.

关 键 词：P2P系统 幂律分布 小世界 泛洪算法 搜索 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]