电信科学 ›› 2015, Vol. 31 ›› Issue (8): 91-98.doi: 10.11959/j.issn.1000-0801.2015197

• 研究与开发 • 上一篇    下一篇

保证响应时间百分比下的云中心资源优化配置

何怀文1,2   

  1. 1 电子科技大学中山学院计算机学院 中山 528402
    2 中山大学信息科学与技术学院 广州 510275
  • 出版日期:2015-08-27 发布日期:2015-08-27
  • 基金资助:
    国家自然科学基金青年科学基金资助项目;广东省自然科学基金博士启动项目基金资助项目;中山市科技计划基金资助项目;中山市科技计划基金资助项目

Optimal Resource Provision of Cloud Center with Guarantee Percentile Response Time

Huaiwen He1,2   

  1. 1 School of Computer,University of Electronic Science and Technology of China Zhongshan Institute,Zhongshan 528402,China
    2 School of Information Science and Technology,Sun Yat-sen University,Guangzhou 510275,China
  • Online:2015-08-27 Published:2015-08-27
  • Supported by:
    The National Natural Science Foundation of China;The Ph D Start-up Fund of Natural Science Foundation of Guangdong Province;The Science and Technology Project of Zhongshan;The Science and Technology Project of Zhongshan

摘要:

为了保证响应时间百分比SLA的同时,最小化商用云中心资源配置成本,基于排队理论提出了云中心模型,从经济角度分析云中心资源配置成本,并推导出云中心响应时间百分比的数学表达式。给出了计算最小配置成本算法(MPCA),通过大量实验分析了负载流量、响应时间百分比和基准响应时间对配置成本的影响。实验结果表明,通过MPCA对云中心服务器数量和运行速率进行优化,可以使配置成本随着负载流量的增加而呈线性增长。

关键词: 响应时间百分比, 云中心, 资源配置, SLA

Abstract:

In order to minimize resource provisioning cost of commercial cloud center,while guarantee percentile response time SLA,a cloud center model based on queuing theory was proposed.Resource provisioning cost was analyzed from an economic point of view,and the mathematical expressions of cloud center percentile response time were deduced.Meanwhile the minimum provisioning cost algorithm(MPCA)was developed to calculate the minimum cost of cloud center,the affect on cloud center cost by load flow,percentile response time and based response time was analyzed via a large number of experiments.The results show that with MPCA to optimized server number and speed of cloud center,it can achieve cost linear increase with increasing traffic load.

Key words: percentile response time, cloud center, resource provision, SLA

No Suggested Reading articles found!