基于多精英协同进化遗传算法的云资源调度  

CLOUD RESOURCE SCHEDULING BASED ON MULTI-ELITE COEVOLUTIONARY GENETIC ALGORITHM

作　　者：魏士伟 邓维 Wei Shiwei;Deng Wei(College of Computer Science and Engineering,Guilin University of Aerospace Technology,Guilin 541004,Guangxi,China)

机构地区：[1]桂林航天工业学院计算机科学与工程学院,广西桂林541004

出　　处：《计算机应用与软件》2021年第5期274-280,共7页Computer Applications and Software

基　　金：广西自然科学基金项目(2016GXNSFAA380226);广西高校中青年教师基础能力提升基金项目(2017KY0866);桂林航天工业学院物联网与大数据应用研究基金项目(KJPT201809)。

摘　　要：传统的遗传算法(GA)在解决云资源调度问题时会随着问题规模的增大而出现早熟收敛、搜索效率低下、寻优能力差等现象。为了克服这些缺陷,提出一种基于多精英协同进化的遗传算法(MECGA)。该算法通过多精英保留技术将适应度值大的个体选入精英子种群,通过与普通子种群进行协同交叉操作,可引导整个种群向最优解的方向移动;通过定义个体评价策略,将差异度高的个体也选入到精英子种群,这些个体又能够保证种群的多样性,使种群更容易跳出局部最优解。实验结果表明,MECGA相较其他GA具有求解效率高、收敛速度快和寻优能力强等特点。When dealing with cloud resource scheduling,the traditional genetic algorithm(GA)becomes more prone to be of premature convergence,low search efficiency and poor search ability as the scale of the problem grows.To overcome the shortcomings,a multi-elite coevolutionary genetic algorithm(MECGA)is proposed.It selected some elite individuals with large fitness values from population and made crossover operation between the elites and the common ones,inducing the whole population to move to the direction of the optimal solution quickly.In addition,some individuals with large dissimilarity degrees were also selected and put into elite subpopulation to ensure the diversity of population,resulting in that MECGA has the ability to jump out of the local optimal solution.The experimental results show that the MECGA has higher efficiency,faster convergence and better search ability than other GA algorithms.

关 键 词：遗传算法 进化算法 精英策略 协同进化 资源调度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]