融合目标空间分割的网格任务调度算法  

A Grid Task Scheduling Algorithm Based on Objective-space-divided Computer Engineering and Applications

作　　者：任长安[1] 李智勇[2] 罗庆云[1] 陈利平[1] 

机构地区：[1]湖南工学院计算机与信息科学学院,湖南衡阳421008 [2]湖南大学信息科学与工程学院,长沙410082

出　　处：《控制工程》2014年第3期441-445,共5页Control Engineering of China

基　　金：国家自然科学基金项目(61173107);湖南省科技计划项目(2013FJ3095);湖南省教育厅科研项目(10C0588)

摘　　要：针对网格环境中多个相互独立的任务调度问题,提出一种融合空间分割思想的网格任务调度算法(OSD-GTSA,a Grid Task-Scheduling Algorithm based on Objective-Space-Divided)。算法结合了OSD-MOEA(A Multiple-Objective Evolutionary Algorithm based on the ObjectiveSpace-Divided)算法的目标空间分割的思想,通过对网格中多个相互独立的任务问题进行建模,针对费用和时间权重的不同,进行了3组仿真实验。实验结果表明,OSD-GTSA在算法的收敛性和Pareto解集的分布性上都取得了满意的效果。As for the problem of multiple-independent-task-scheduling in grids, this thesis proposes a Grid-task-Scheduling Algorithm based on objective-space-divided（OSD-GTSA）. This OSD-GTSA adopts the thoughts of division and sorting of the space of the OSD- MOEA. By building model of the problem of multiple-independent-task-scheduling in grids, the author makes three relevant simulation experiments considering the differences in the reliance on cost and time. And the results of the experiments prove that the OSD-GTSA has got satisfied results in both the convergence of algorithm and the distribution of Pareto solution set.

关 键 词：进化算法 目标空间分割 网格任务调度 时间 费用 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]