基于多目标演化算法的云计算虚拟机分配策略研究  

Research of Cloud Computing Virtual Machine Allocated Strategy on Multi-objective Evolutionary Algorithm

作　　者：艾浩军[1] 龚素文 袁远明[1] 

机构地区：[1]武汉大学计算机学院,武汉430072 [2]九江职业技术学院,九江332007

出　　处：《计算机科学》2014年第6期48-53,共6页Computer Science

基　　金：国家科技支撑计划(2012BAH35B03)资助

摘　　要：分析云计算虚拟机资源模型,针对模型中虚拟机与物理机的映射关系以及虚拟机多资源因子、多优化目标的特点,将虚拟机分配问题转化成多维装箱问题,引入多目标演化算法进行求解。算法设计了基于组的虚拟机分配链式编码和染色体评估函数,并根据编码设计了两种交叉算子和智能变异算子,通过引入基于超体积的种群更新机制,设计了基于SMS-EMOA的云计算虚拟机分配算法。为验证SMS-EMOA的性能,分别使用优先匹配启发式算法、基于物理节点数量的单目标简单遗传算法、SMS-EMOA进行了模拟。实验结果表明,基于SMS-EMOA的虚拟机分配算法在性能上更优。The thesis analyzed cloud computing virtual machine resource model,and aiming at the mapping between virtual machines and physical machines in the model,and the characteristics of virtual machine multi-resource factor and multi-objective optimization,translated the virtual machine allocation problem into multi-dimensional packing problem,introduced multi-objective evolutionary algorithm to solve problem.Firstly,the algorithm designs the growing chain coding and chromosome evaluation function for virtual machine distribution problem,and according to the Encoding,designs two crossover operators and a smart mutation operator,finally,introduces the Hypervolume Measure as population selection Criterion,and designs cloud virtual machine allocation algorithm based on SMS-EMOA.In order to verify the performance of SMS-EMOA,the simulation experiment was made using PMH,CGA,SMS-EMOA,and the experimental results show that SMS-EMOA is better in virtual machine allocation performance.

关 键 词：云计算 虚拟机分配 多目标演化算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]