CORC  > 清华大学
一种基于期货市场理论的网格资源分配机制
刘会斌 ; 都志辉 ; LIU Hui-Bin ; DU Zhi-Hui
2010-06-09 ; 2010-06-09
关键词网格资源分配 期货 任务调度 Grid resource allocation,Futures,Task scheduling TP393.07
其他题名A Grid Resources Allocation Mechanism Based on Futures Markets Theory
中文摘要在比较了计算网格资源和期货特点的基础上,提出了一种基于期货市场理论的网格资源分配机制,避免了现货市场价格的大幅波动。提出了基于期货市场的资源竞价交易算法,通过在电力网格系统上的模拟实验以及与“蛛网模型”的对比,表明本文提出的竞价算法具有资源的利用率高、稳定性高的优点。针对资源域内任务调度,提出了基于期货合约任务调度算法,通过实验比较了群集循环法、先来先服务、Max-min调度算法的完成时间,基于期货合约的任务调度算法完成时间最短。最后讨论了网格技术及期货市场理论在电力系统的应用。; After comparing the characteristics of grid computing resource and futures,a grid resource allocation mechanism based on futures markets theory is presented. Simulation results show that futures market model can avoid price fluctuating .A new allocation algorithm based on competition is proposed. The performance of the allocation algorithm based on competition and coweb model is compared by experiments.The experimental results indicate that the algorithm based on competition is more stable with higher utilization ratio of the grid resource. A scheduling algorithm based on futures contract within a domain of grid resource is presented. The performances of the scheduling algorithm based on futures contract,first come first served model,Cluster Round robin algorithm and Max-min scheduling algorithm are compared by experiments, and the experimental results indicate that the scheduling algorithm based on futures contract algorithm can attain the shortest response time among them. Grid computing,futures markets theory and its application in power system are also discussed.; 国家重点基础研究计划(973计划)“提高大型互联电网运行可靠性的基础研究”子课题“大型互联电网分布式计算理论和方法研究”(课题编号:2004CB217903); 863仿真应用网格项目“仿真网格的应用研究与开发”(课题编号:2004AA104330)的资助。
语种中文 ; 中文
内容类型期刊论文
源URL[http://hdl.handle.net/123456789/56336]  
专题清华大学
推荐引用方式
GB/T 7714
刘会斌,都志辉,LIU Hui-Bin,等. 一种基于期货市场理论的网格资源分配机制[J],2010, 2010.
APA 刘会斌,都志辉,LIU Hui-Bin,&DU Zhi-Hui.(2010).一种基于期货市场理论的网格资源分配机制..
MLA 刘会斌,et al."一种基于期货市场理论的网格资源分配机制".(2010).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace