蚁群算法解决网格环境下任务调度问题的研究  

Research on Solving the Problem of Task Scheduling in Grid Envi ronment by Ant Colony Algorithm

作　　者：赵飞[1] 吴航[1] 龚跃[1] 

机构地区：[1]长春理工大学计算机科学技术学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2013年第1期97-100,共4页Journal of Changchun University of Science and Technology(Natural Science Edition)

摘　　要：网格环境下的任务调度是典型的NP难组合优化问题,是近些年来学者们争相研究的热点。传统的Min-Min算法具有任务完成时间长,负载平衡性差等缺点,因此,本文提出了一种应用蚁群算法解决该问题的方法。利用蚂蚁总能从蚁穴到食物源之间找到最短路径这一自然特性,将任务的一次分配过程抽象为蚂蚁的一次探路过程,最终得到较优的分配结果,并进行了实验仿真模拟,取得了不错的效果。Task scheduling in grid environment is a typical NP-hard combinatorial optimization problem, and has been the focus which scholars study intensely in recent years. The traditional Min-Min algorithm has the defects such as long task completing time and poor load balance performs, therefore we propose using ant colony algorithm to solve the problem. According to the nature by which that ants can always find the shortest path from the cave to the food source, one task allocation process is abstracted as a path finding procedure of ants allocation and experimental simula- tion results wene obtained.

关 键 词：网格 任务调度 MIN-MIN算法 蚁群算法 

分 类 号：TH164[机械工程—机械制造及自动化]