网格资源超图划分聚类任务调度  

Resource Hypergraph Partitioning Clustering Grid Task Scheduling

作　　者：陈志刚[1] 杨博[1] 刘立[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410083

出　　处：《小型微型计算机系统》2008年第9期1599-1603,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(60573127)资助;教育部创新团队项目(IRT0661)资助

摘　　要：网格计算是当前一个活跃的研究领域,其中任务调度是实现网格计算目标的一个重要部分.为获得良好的网格任务调度性能,提出了一种基于资源超图划分聚类的网格任务调度算法RHPC.该算法根据网格环境下资源数量庞大、异构、多样的特点,在构建的网格资源超图模型基础上,预先对资源进行性能划分聚类,将任务与聚类资源相匹配并实施调度.模拟实验结果证明算法缩短了任务资源相匹配的时间,提高了任务调度的性能,是一种有效的网格任务调度算法.Grid computing is currently an active research area and task scheduling is an important part to realize the object of Grid computing. A resource hypergraph partitioning clustering based Grid task scheduling algorithm, RHPC, is proposed for getting a favorable performance of Grid task scheduling. In the algorithm, resource performance partitioning clustering is done in advance based on Grid resource hypergraph model constructed according to characteristics of resources in Grid such as giant numbers, heterogeneity and multiplicity, and tasks are matched to clustering resources and scheduled. Simulation results show that it is a effective Grid task scheduling algorithm that shortens the matching time between the task and the resource and improve the performance of task scheduling.

关 键 词：网格 任务调度 超图 划分 聚类 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]