基于最大收益平衡点动态变化的云资源调度算法  

Cloud resource scheduling algorithm based on dynamic change of maximum profit equilibrium

作　　者：张爱科[1] 符保龙[1] 

机构地区：[1]柳州职业技术学院,广西柳州545006

出　　处：《重庆邮电大学学报（自然科学版）》2014年第5期706-711,共6页Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)

基　　金：广西教育厅科研项目基金资助(201106LX745);广西教育厅科研项目基金资助(201204LX593)~~

摘　　要：云计算中资源调度是云计算高效利用的核心问题,主要研究如何对云端的资源进行有效地管理和调度。以从服务商需求的角度构建云资源调度的方法为切入点,从服务商的角度出发,在不损害用户和生产商利益的前提下,介入收益、成本、边际收益、边际成本等因素,以节省资源并获得服务商的最大收益为优化目的,根据最大收益平衡点随着负载变化的动态变化,构建了一种基于动态平衡点动态变化的云资源调度算法。通过比较当前周期和上一周期的边际收益变化,动态更新最大收益平衡点的位置,根据此位置对应的参数完成云资源调度。通过CloudSim平台下的仿真实验表明,该方法比基于服务驱动的调度方法具有更快的响应、使用更少的虚拟机、能获得更大的收益。Cloud resource scheduling was the core problem of efficient utilization of cloud computing, which is mainly on how to effectively manage and schedule for cloud resources. In this paper, from the angle of the service provider who needs to build the cloud resource scheduling method as the breakthrough point, and from the perspective of service providers, on the premise of not damaging the interests of users and manufacturers, the benefits, costs involved, marginal revenue, marginal cost and other factors are introduced. In order to save resources and obtain maximum profit for service providers, a new cloud resource scheduling method was proposed according to the changes of maximum profit equilibrium point with load change. By comparing current period and last period＇ s marginal income changes, maximum profit equilibrium point was dynamic updated. And cloud resource was scheduled according to the parameters of the corresponding position. Experimental results show that the proposed method had a faster response and less number of virtual machine and could get more income than scheduling method based on service driving.

关 键 词：云资源调度 动态平衡 最大收益 虚拟机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]