基于多目标蚁群优化的虚拟机放置算法  

Virtual Machine Placement Algorithm Based on Multi-objective Ant Colony Optimization

作　　者：黎海雪 林海涛[1] 丁泽柳 LI Haixue;LIN Haitao;DING Zeliu(College of Electronic Engineering,Naval college of Engineering,Wuhan 430033)

机构地区：[1]海军工程大学电子工程学院,武汉430033

出　　处：《计算机与数字工程》2018年第12期2445-2449,共5页Computer & Digital Engineering

基　　金：湖北省自然科学基金"新型结构云数据中心网络研究"(编号:2016CFB287)资助

摘　　要：针对目前对云数据中心虚拟机放置算法大多为优化能耗和考虑单目标,很少综合考虑多个目标的优化,论文提出了一种多目标蚁群优化放置算法来解决该问题。首先,形式化描述能量消耗、资源浪费、能量通信成本最小化为目标,提出了多目标蚁群优化放置算法;然后建立了蚁群优化算法数学模型;最后通过CloudSim平台进行仿真实验。仿真表明,相比FFD、DVFS、LR和MGA等传统虚拟机放置算法,该文提出的算法具有更高的性能优势。In view of the existing cloud data center virtual machine placement is mostly to optimize energy consumption and consider a single goal,rarely consider multiple goals optimization,multi-objective ant colony optimization(MACO)placement algo?rithm to solve this problem is proposed.Firstly,it is proposed to formally describe energy consumption,resource waste and energy communication cost minimization.Then,the mathematical model of ant colony optimization algorithm is established.Finally,Simu?lation experiments are carried out on clouds implatform.Simulation results show that the proposed algorithm has better performance than First-Fit Decreasing(FFD),Dynamic Voltage and Frequency Scaling(DVFS),Local Regression(LR),Multi Objective Genetic Algorithm(MGA)and other traditional virtual machine placement algorithms.

关 键 词：云计算 虚拟机放置 资源映射 蚁群优化算法 

分 类 号：O221.6[理学—运筹学与控制论]