计算机工程与应用 ›› 2014, Vol. 50 ›› Issue (17): 56-62.

• 理论研究、研发设计 • 上一篇    下一篇

基于随机模型的云平台资源调度策略设计

赵少卡1,2,李立耀1,徐  聪2,杨家海2   

  1. 1.福建师范大学福清分校 数学与计算机科学系,福建 福清 350300
    2.清华大学 网络科学与网络空间研究院,北京 100084
  • 出版日期:2014-09-01 发布日期:2014-09-12

Cloud platform resource scheduling strategy design based on stochastic model

ZHAO Shaoka1,2, LI Liyao1, XU Cong2, YANG Jiahai2   

  1. 1.Department of Mathematics and Computer Science, Fuqing Branch of Fujian Normal University, Fuqing, Fujian 350300, China
    2.Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China
  • Online:2014-09-01 Published:2014-09-12

摘要: 针对云计算资源管理的实际需求,提出一种基于随机模型的云平台调度策略,设计合理高效的资源调度算法,解决传统代数模型请求丢失率高以及其他随机模型负载均衡指标性能较差的问题,从而在服务性能和执行效率的基础上保证服务器的资源负载,使云平台处于相对稳定的状态。在实验环境中的验证结果表明,该调度策略能够优化虚拟资源的使用效率和服务响应时间,同时能够达到较好的负载均衡并降低运营成本。

关键词: 云计算, 资源调度, 负载均衡, 随机模型

Abstract: In view of cloud computing actual needs of resource management, cloud platform scheduling strategy based on stochastic model is proposed, and reasonable and efficient resource scheduling algorithm is designed in order to reduce the request loss rate of traditional algebraic model and improve poor load balancing performance of other stochastic models. Through load balancing on the basis of service performance and efficiency, cloud platform stability is ensured. Experimental results show that the scheduling strategy can optimize the efficiency of virtual resource usage and the response time of the service while being able to achieve better load balance and reduce operating costs.

Key words: cloud computing, resource scheduling, load balancing, stochastic model