一种改进的自适应云遗传算法  

Improved Adaptive Cloud Genetic Algorithm

作　　者：韩勇[1] 曹兴华[1] 杨煜普[1] 

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240

出　　处：《计算机仿真》2011年第10期191-194,198,共5页Computer Simulation

基　　金：国家"973"计划基金资助项目(2004CB720703)

摘　　要：关于优化云计算方法问题,需研究一种改进的自适应云遗传算法,针对传统云遗传算法(CGA)中对交叉及变异过程中的云模型控制参数取定值导致算法存在"早熟"及收敛速度慢的问题。为了解决上述问题,在CGA的基础上提出一种自适应云遗传算法(ACGA),引入在线性与非线性间平滑过渡的自适应子算子,使得控制参数根据种群适应度进行自适应调整,并通过性能分析证明了算法的正确性。仿真结果表明,通过与GA及CGA算法的比较,ACGA在收敛性能和搜索能力上都有很大的提高。An improved adaptive cloud genetic algorithm is proposed.In view of the shortcomings of CGA that taking fixed control value in cloud model will lead premature and low convergence speed,this paper presents an Adaptive Cloud Model Based Genetic Algorithm（ACGA） that introduces adaptive operator between linear and non-linear to solve the problem of geting the proper value of the control parameters in the process of crossover and mutation.In ACGA,the control parameters are adaptively adjusted according to population fitness.Its correctness has been proved by the performance analysis.The result of the simulation shows that compare with GA and CGA,ACGA is of better converging and searching abilities.

关 键 词：云模型 自适应参数 种群适应度 函数优化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]