摘要
针对云计算中的任务调度问题,提出了一种任务调度的增强蚁群算法(task scheduling-enhanced ant colony optimization,TS-EACO)。算法兼顾了任务调度的最短完成时间和负载平衡,同时参考了近年来蚁群算法的各种改进,创新地将任务在虚拟机上的一次分配作为蚂蚁的搜索对象。实验在CloudSim仿真平台下进行,并将仿真结果与Round Robin算法和标准蚁群算法进行比较,结果表明TS-EACO算法的任务执行时间和负载平衡性能均优于这两种算法。
To deal with problems for task schedule of cloud computing, a design method of task scheduling enhanced ant colony optimization （task scheduling-enhanced ant colony optimization, TS-EACO） algorithm is proposed. A balance of the minimum execution time and load balance of task schedule are gotten of this algorithm. The TS-EACO also absorbs the advantages of some refine ant colony algorithms occurred recent years. An allocation of a task for a virtual machine is an object that the ant would search. Some experiments are done on the CloudSim platform. The results of three different algorithms are compared. The comparison shows the execution time and load balance of TS-EACO are better than those of others.
出处
《计算机工程与设计》
CSCD
北大核心
2013年第5期1716-1719,1816,共5页
Computer Engineering and Design
基金
国家自然科学基金项目(61071093)
南京工业职业技术学院院级基金项目(YK10-02-07)
关键词
云计算
任务调度
资源分配
蚁群优化
云仿真
cloud computing
task scheduling
resource allocation
ant colony optimization
cloud simulation
