通信学报 ›› 2019, Vol. 40 ›› Issue (6): 102-115.doi: 10.11959/j.issn.1000-436x.2019113

• 学术论文 • 上一篇    

基于利益相关视角的多维QoS云资源调度方法

苏命峰1,王国军2(),李仁发3   

  1. 1 中南大学计算机学院,湖南 长沙 410083
    2 广州大学计算机科学与网络工程学院,广东 广州510006
    3 湖南大学信息科学与工程学院,湖南 长沙 410082
  • 修回日期:2019-02-08 出版日期:2019-06-01 发布日期:2019-07-04
  • 作者简介:苏命峰(1980- ),男,湖南宁乡人,中南大学博士生,主要研究方向为云计算、边缘计算、云-端协同计算等。|王国军(1970- ),男,湖南长沙人,博士,广州大学教授、博士生导师,主要研究方向为云计算、边缘计算、云-端协同计算等。|李仁发(1957- ),男,湖南宜章人,博士,湖南大学教授、博士生导师,主要研究方向为云计算、嵌入式系统、无线传感网等。
  • 基金资助:
    国家自然科学基金资助项目(61632009);国家自然科学基金资助项目(61472451);国家自然科学基金资助项目(61672217);湖南省自然科学基金资助项目(2019JJ70057);广东省自然科学基金资助项目(2017A030308006);广东省高等教育高层次人才计划基金资助项目(2016ZJ01);中南大学中央高校基本科研业务费专项资金基金资助项目(2018zzts180)

Multidimensional QoS cloud computing resource scheduling method based on stakeholder perspective

SU Mingfeng1,WANG Guojun2(),LI Renfa3   

  1. 1 School of Computer Science and Engineering,Central South University,Changsha 410083,China
    2 School of Computer Science and Cyber Engineering,Guangzhou University,Guangzhou 510006,China
    3 College of Computer Science and Electronic Engineering,Hunan University,Changsha 410082,China
  • Revised:2019-02-08 Online:2019-06-01 Published:2019-07-04
  • Supported by:
    The National Natural Science Foundation of China(61632009);The National Natural Science Foundation of China(61472451);The National Natural Science Foundation of China(61672217);The Natural Science Foundation of Hunan Province(2019JJ70057);The Natural Science Foundation of Guangdong Province(2017A030308006);The High-Level Talents Program of Higher Education of Guangdong Province(2016ZJ01);The Fundamental Research Funds for the Central Universities of Central South University(2018zzts180)

摘要:

基于云用户和云服务提供商的利益相关视角,以低计算成本(如能耗、经济成本和系统可用性等)满足云用户高QoS需求(如任务执行时间和任务最终完成时间),设计多维QoS云计算体系结构,构建多维QoS云资源调度模型,面向二级云资源调度,提出采用多重Greedy算法思想的MQoS云资源调度算法。实验结果表明,在具有无后效性的4种云计算应用场景下,MQoS云资源调度算法相比FIFO云资源调度算法、M2EC多维能耗虚拟机调度算法,其多维QoS度总体提升206.42%~228.99%、34.26%~56.93%,其云数据中心负载均衡差平均总体降低0.48~0.49、0.20~0.27。

关键词: 云计算, 资源调度, 多目标优化, 利益相关视角, 多维服务质量

Abstract:

A multidimensional cloud computing architecture is designed and a multidimensional cloud resource scheduling model is constructed based on the stakeholder perspective of cloud users and cloud service providers to meet the high QoS requirements of cloud users (such as task execution time and task completion time) with low computing costs (such as energy consumption,economic costs and system availability).For the second-level cloud resource scheduling,an MQoS cloud resource scheduling algorithm based on multiple Greedy algorithm is proposed.The experimental results show that under the four cloud computing application scenarios with no aftereffects,the MQoS cloud resource scheduling algorithm has an overall increase of 206.42%~228.99% and 34.26%~56.93 in terms of multidimensional QoS degree compared with FIFO and M2EC algorithms.It has an average overall reduction of 0.48~0.49 and 0.20~0.27 in terms of cloud data center load balance difference.

Key words: cloud computing, resource scheduling, multi-objective optimization, stakeholder perspective

中图分类号: 

  • TP393