基于改进蚁群算法的云计算任务调度模型  

Cloud Computing Task Scheduling Model Based on Improved Ant Colony Algorithm

作　　者：魏赟[1] 陈元元[1] 

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《计算机工程》2015年第2期12-16,共5页Computer Engineering

基　　金：国家自然科学基金资助项目(61170277);上海市教委科研创新基金资助项目(12YZ094)

摘　　要：为解决云环境下的资源调度问题,提出一种能改善任务并行性与兼顾任务串行关系的调度模型,将用户提交的动态任务分割成具有制约关系的子任务,按运行次序放到具有不同优先级的调度队列中。针对同一调度队列中的子任务,采用基于最短任务延迟时间的改进蚁群算法(DSFACO)进行调度,在兼顾调度公平性与效率的前提下,最大化缩短任务延迟时间,从而提高用户满意度。实验结果表明,与任务调度增强蚁群算法相比,DSFACO算法在任务延迟时间、调度公平性及效率方面性能更好,能实现云计算环境下任务的最优调度。To solve the problem of resource scheduling problem in cloud computing,a parallel scheduling model is proposed,which can improve the task parallelism while maintaining the serial relationships between tasks.Dynamic tasks submitted by users are divided into sub-tasks in some serial sequences,and it puts into scheduling queue with different priorities according to running order.For these tasks in the same priority scheduling queue,an improved Delay Time Shortest and Fairness Ant Colony Optimization（DSFACO） algorithm is applied to schedule.Considering both fairness and efficiency,DSFACO algorithm applies to subtask scheduling problem to realize shortest delay time,thus improves the user satisfaction.Experimental results show DSFACO algorithm is better than the TS-EACO algorithm in fairness,efficiency and task delay time,and it can realize the optimal scheduling in cloud computing.

关 键 词：云计算 蚁群算法 任务调度 公平性 任务延迟时间 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]