一种基于历史交易记录和个体负载的分布式资源定价方法  

History Information and Individual Load Based Distributed Resource Pricing Method

作　　者：王恩泽[1] 乔建忠[1] 林树宽[1] 

机构地区：[1]东北大学信息科学与工程学院,沈阳110819

出　　处：《小型微型计算机系统》2016年第2期246-251,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61075021)资助

摘　　要：应用经济理论解决分布式资源分配问题一直是分布式计算领域的研究热点,其焦点是如何合理定价.目前的定价模型通常考虑资源成本、供求情况等因素对于资源价格的影响.本文通过对现有定价方法和资源分配算法的研究,提出一种基于历史交易记录和个体负载的分布式资源定价方法(HIILDPM),更符合分布式计算的特征;在此基础上设计了一种资源分配算法HIIL-CDA.结果表明,HIILDPM与现有定价方法相比具有较好的价格收敛性,较高的资源利用率和执行效率.To utilize economic theory to solve distributed resource allocation problem is always a research focus, how to pricing re- sources reasonably is the core issue. The present pricing methods usually took resource cost, supply and demand, and other factors un- der consideration. This paper proposed a history information and individual load based distributed resource pricing method （ HIILD- PM） by researching the present pricing methods and resource management algorithms. HIILDPM is more suitable to the characteristics of distributed computing. A resource allocation algorithm called HIIL-CDA is designed based on HIILDPM. The result showed that HI- ILDPM has better price convergence,resource utilization and execution efficiency than the present pricing methods.

关 键 词：分布式计算 资源分配 经济理论 定价方法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]