计算机工程与应用 ›› 2014, Vol. 50 ›› Issue (6): 51-55.

• 理论研究、研发设计 • 上一篇    下一篇

云计算环境下基于遗传蚁群算法的任务调度研究

张  雨,李  芳,周  涛   

  1. 上海理工大学 管理学院,上海 200090
  • 出版日期:2014-03-15 发布日期:2015-05-12

Task scheduling algorithm based on genetic ant colony algorithm in cloud computing environment

ZHANG Yu, LI Fang, ZHOU Tao   

  1. College of Management, University of Shanghai for Science and Technology, Shanghai 200090, China
  • Online:2014-03-15 Published:2015-05-12

摘要: 对云计算中任务调度进行了研究,针对云计算的编程模型框架,提出一种融合遗传算法与蚁群算法的混合调度算法。在该求解方法中,遗传算法采用任务-资源的间接编码方式,每条染色体代表一种具体调度方案;选取任务平均完成时间作为适应度函数,再利用遗传算法生成的优化解,初始化蚁群信息素分布。既克服了蚁群算法初期信息素缺乏,导致求解速度慢的问题,又充分利用遗传算法的快速随机全局搜索能力和蚁群算法能模拟资源负载情况的优势。通过仿真实验将该算法和遗传算法进行比较,实验结果表明,该算法是一种云计算环境下有效的任务调度算法。

关键词: 云计算, 蚁群算法, 遗传算法, 任务调度

Abstract: How to schedule masses of tasks efficiently is an important issue to be resolved in cloud computing environment. An algorithm combining Genetic Algorithm(GA) and Ant Colony algorithm(ACO) is brought up for the programming framework of cloud computing. In the algorithm, the GA adopts task-worker coding method, every chromosome representing a specific scheduling scheme, and chooses the average completing time of all tasks as its fitness function. Then the ACO adopts Genetic Algorithm to give initial information pheromone to distribute. This combination not only overcomes the slow speed of ACO caused by lack of information pheromone on the path early, but also takes full use of GA, that is fast-speed, randomly and global search. There is a contrast between GA and the combined algorithm through simulation experiment, and the result shows the proposed algorithm is efficient in the cloud computing environment.

Key words: cloud computing, ant colony algorithm, Genetic Algorithm(GA), task scheduling