一种基于任务分解的时间均衡调度算法  

A time-balancing scheduling algorithm based on task decomposition

作　　者：魏妮妮 宋翌[1] 

机构地区：[1]武汉生物工程学院计算机与信息工程系,湖北武汉430415

出　　处：《河北科技大学学报》2013年第6期559-564,共6页Journal of Hebei University of Science and Technology

基　　金：湖北省自然科学基金(2011CD297);武汉市教育局科研项目(2009k100);武汉市教育局科研项目(2009k101)

摘　　要：网格环境下的任务调度是一个NP完全问题,它一直是网格领域研究的核心。针对计算网格中的任务放牧调度这类问题,提出了一种基于任务分解的时间均衡调度算法。该算法在调度过程中充分考虑了网格资源的特点,采用重复调度和任务分解策略,并进行了仿真实验。在任务完成时间和系统吞吐率两方面与Max-min和Max-int算法进行比较,实验结果证明该算法优于Maxmin和Max-int,是一种性能较好的任务调度算法。Task scheduling is a NP-completed problem in the gird environment,and it is the key issue on gird computing.In this paper,an algorithm based on task decomposition and time-balancing is proposed,and it aims at scheduling problem of the task grazing in gird computing.The algorithm fully considers features of the gird resources in the scheduling.The remapping and task decomposition strategy are applied.In order to verify the performance,simulated experiments are conducted.As for the completion time and system resource utilization,the performance is compared with the Max-min and Max-int algorithm. The experimental results show that the algorithm is better than the compared algorithms.

关 键 词：网格计算 任务调度 任务分解 时间均衡 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]