摘要： 当前云计算虚拟化平台无法适用于对时延要求较高的应用。为此，提出一种基于粒子群优化算法的虚拟机放置策略。介绍粒子群优化算法，建立云环境内部时延模型，设计虚拟机放置策略架构。实验结果表明，该策略的请求响应时间比动态资源调度(DRS)策略降低14%~19%，每秒处理请求数比DRS方案提高约17%。

关键词: 云计算, 虚拟机放置, 粒子群优化算法, 时延, 工作流

Abstract: Currently, the virtual machine placement strategy of cloud computing perform is not well in the low delay require. In order to solve this problem, this paper proposes a new virtual machine placement strategy based on Particle Swarm Optimization(PSO) algorithm. It introduces the PSO algorithm, designs a delay model in cloud environment, and combines them to get virtual machine placed scheme. Experimental results show that the response time is less than Dynamic Resource Scheduler(DRS) by 14%~19%, and the Requests per Second(RPS) is more by 17%.

Key words: cloud computing, virtual machine placement, Particle Swarm Optimization(PSO) algorithm, delay, workflow

中图分类号: 

• TP301.6