云基础设施利润驱动的多目标虚拟机资源调度  

Cloud infrastructure profit driven multi-objective virtual machine scheduling

作　　者：胡丹丹[1] 陈宁江[1] 朱莉蓉[1] 谭瑛[1] 李湘[1] 

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《广西大学学报（自然科学版）》2014年第3期641-649,共9页Journal of Guangxi University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(61063012;61363003);广西自然科学基金资助项目(2012GXNSFAA053222);广西高校优秀人才资助计划([2011]40);广西科学研究与技术开发计划项目(桂科攻1348020-7;桂科软13180015)

摘　　要：为研究在云服务模式中虚拟机资源数目和调度对基础设施提供商(Infrastructure Provider,IP)的利润影响,建立了云基础设施提供商的利润模型,并根据微观经济学的原理,计算使云基础设施提供商利润最大化的虚拟机资源数目。引入粒子群算法,对数据中心虚拟机资源的调度进行建模分析,根据客户需求和当前数据中心的负载状态,以最大化资源利用率、最小化所占用物理机的数目和虚拟机迁移次数为目标,提出了基于增强型多目标粒子群算法的虚拟机资源调度策略EPSO-VM。实验结果表明,该策略能够提高资源利用率,降低占用物理机数目和虚拟机迁移次数,以提高IP的利润。In order to study the profit effects of virtual machine resources and scheduling of the Infrastructure Provider（ IP） in the cloud,an Infrastructure Providers＇ profit model is established,and based on the principle of microeconomics the number of virtual machines is calculated to maximize the profit of Infrastructures Providers. By using the particle swarm optimization theory,the virtual machine resource scheduling in the data center is modeled and analyzed. Based on the demands of users and the current workload of the data center,an Enhanced Multi-Objectives Particle Swarm Optimization based Virtual Machine Scheduling Strategy（ named EPSO-VM） is presented,to achieve the goals including maximizing resource utilization,minimizing the number of occupied physical machines and virtual machine migrations,The experimental result shows that EPSO-VM can improve resource utilization,and reduce the number of occupied physical machines and virtual machine migrations so as to increase profit of Infrastructure Providers.

关 键 词：云服务 利润驱动 虚拟机 资源调度 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]