计算机应用 ›› 2013, Vol. 33 ›› Issue (08): 2147-2150.

• 先进计算 • 上一篇    下一篇

云计算中基于优先级和费用约束的任务调度算法

武小年1,邓梦琴1,张明玲1,曾兵2   

  1. 1. 桂林电子科技大学 信息与通信学院,广西 桂林 541004
    2. 保密通信重点实验室,成都 610041
  • 收稿日期:2013-02-07 修回日期:2013-03-30 出版日期:2013-08-01 发布日期:2013-09-11
  • 通讯作者: 武小年
  • 作者简介:武小年(1972-),男,湖北监利人,副教授,硕士,主要研究方向:分布式计算、信息安全;
    邓梦琴(1987-),女,江西南昌人,硕士研究生,主要研究方向:任务调度;
    张明玲(1985-),女,山东枣庄人,硕士研究生,主要研究方向:任务调度;
    曾兵(1974-),男,四川成都人,副研究员,硕士,主要研究方向:信息安全。
  • 基金资助:

    国家自然科学基金资助项目;保密通信重点实验室基金资助项目;广西自然科学基金资助项目;广西教育厅基金资助项目;广西研究生教育创新计划项目

Task scheduling algorithm based on priority and cost constraint in cloud computing

WU Xiaonian1,DENG Mengqin1,ZHANG Mingling1,ZENG Bin2   

  1. 1. School of Information and Communication, Guilin University of Electronic Technology, Guilin Guangxi 541004, China
    2. Science and Technology on Communication Security Laboratory, Chengdu Sichuan 610041, China
  • Received:2013-02-07 Revised:2013-03-30 Online:2013-09-11 Published:2013-08-01
  • Contact: WU Xiaonian

摘要: 针对云计算中的服务质量保证问题,提出一种基于优先级和费用约束的任务调度算法。该算法通过计算任务优先级和资源服务能力,分别对任务和资源进行排序和分组,并根据优先级高低和服务能力强弱建立任务组和资源组间的调度约束关联;再通过计算任务在关联资源组内不同资源上的完成时间和费用,将任务按优先级高低依次调度到具有任务完成时间和费用折中值最小的资源上。与Min-Min和QoS-Guided-Min算法的对比实验结果表明,该算法具有良好的系统性能和负载均衡性,并降低了服务总费用。

关键词: 云计算, 任务调度, 服务质量, 优先级, 费用约束

Abstract: Concerning the service quality assurance in cloud computing, a task scheduling algorithm based on priority and cost constraint was proposed. Firstly, it computed the priority of tasks and the service ability of resources, then made sorting and grouping for tasks and resources respectively, and set the scheduling constrained relationship according to the priority and service ability between task groups and resource groups. Furthermore, the completion time and cost of tasks spent on different resources located in the related resource group were calculated, and finally each task was scheduled in turn onto a resource with minimum time-cost tradeoff value according to its priority. The simulation results show that, compared with Min-Min and QoS-Guided-Min, the proposed algorithm achieves better performance and load balancing, and reduces the overall service cost.

Key words: cloud computing, task scheduling, Quality of Service (QoS), priority, cost constraint

中图分类号: