基于结构化P2P网络的计算力资源整合方法的研究与实现  

Research and Realization of Computing Power Integration in Structured P2P Networks

作　　者：钮麟[1,2] 刘业[1,2] 庄艳艳[1,2] 刘林峰[1,2] 

机构地区：[1]东南大学计算机网络和信息集成教育部重点实验室,南京210096 [2]东南大学计算机科学与工程学院,南京210096

出　　处：《计算机科学》2008年第5期18-23,59,共7页Computer Science

基　　金：面向服务的Overlay网络及其关键技术的研究(编号60573133)的资助

摘　　要：结构化P2P网络因其查找效率高、资源消耗少的特点受到了越来越多的关注,但由于缺少易于开发和应用的平台,结构化P2P网络上的应用还没有广泛出现,这限制了结构化P2P网络的普及。本文研究了结构化P2P网络在计算力资源整合应用上的优势,提出了一种基于结构化P2P网络的计算力资源整合方法,面向系统性能、可靠性、缩放性进行了优化,设计并开发了相应的原型系统。对该方法进行了理论分析和实验验证。结果表明,这一方法有效地整合了网络中节点的计算力,并对网络动态变化和负载均衡有较强的适应能力。Structured P2P networks have attracted more and more attention for their high efficiency and low resource consumption. Due to the lack of a platform for easy development, the applications of structured P2P networks have not been widely appeared which limits their popularization. This paper studies the advantages of integrating computing power based on structured P2P networks and proposes a novel methodology to integrate computing power in structured P2P networks, develops a prototype which is optimized for system performance, reliability and scalability. Analysis is done in both theoretical and experimental scenarios. The results show that this methodology integrates the computing power of the nodes in the network effectively, and is adaptive to the dynamics of the network and load balancing.

关 键 词：结构化P2P网络 计算力资源整合 负载均衡 

分 类 号：TP393[自动化与计算机技术—计算机应用技术] F270[自动化与计算机技术—计算机科学与技术]