针对访问成功率的P2P动态网络对象定位模型  

A P2P Objects Location Model for Higher Access Success Rate over Dynamic Networks

作　　者：綦宏伟[1] 代亚非[1] 李晓明[1] 

机构地区：[1]北京大学计算机科学技术系,北京100871

出　　处：《软件学报》2005年第5期894-902,共9页Journal of Software

基　　金：国家自然科学基金;国家重点基础研究发展规划(973)~~

摘　　要：针对网络海量存储系统的应用需求,提出了一个基于Peer-to-Peer思想的对象分布和定位模型,能够支持众多节点自发组成的动态网络结构.对该模型进行了比较完整的论述,依次建立了全局映射关系、路由表、对象定位和路由算法、对象索引分布方案和节点加入、退出时的维护算法,特别是提出了新的对象索引分布方案,提高了对象的平均访问成功率,围绕此方案,对模型的各组成部分进行了改进,实现了提出的5个性质.最后,通过建立模拟程序,验证了模型的分析预测结果,能够提供均衡的负载分布和较好的对象访问效率.According to the requirement of network massive storage applications, this paper puts forward a P2P based objects distribution and location model, supporting the logic network dynamically composed by a large number of voluntary nodes. The model is discussed in detail as follows: global mapping relation, routing table, object locating and routing algorithm, object indices distribution scheme, and maintenance algorithm when nodes join and leave the network. In particular, a novel scheme for distributing objects indices is provided to improve the average success rate of objects access, and each part of the model is improved. Through analysis, the model fulfills the five objectives given in the introduction. Finally, a simulation program built on this model verifies the expected abilities for balancing the load distribution and improving the objects access efficiency.

关 键 词：peer-to—peer 对象定位 对象索引分布 全局映射关系 路由表 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]