一种基于子群变异的粒子群优化算法  

New particle swarm optimization based on subswarm mutation

作　　者：袁晗[1] 徐春梅 杨平[1] 许姗姗[1] 

机构地区：[1]上海电力学院自动化工程学院,上海200090

出　　处：《计算机应用研究》2017年第4期1076-1079,共4页Application Research of Computers

基　　金：上海市电站自动化技术重点实验室资助项目(13DZ2273800);上海市科技创新行动计划资助项目(13111104300)

摘　　要：为克服粒子群优化算法早熟收敛,提出一种基于子群变异的改进粒子群优化算法(Ss MPSO)。该算法提出一种具有随机定向振荡式搜索的子群对主群的全局最优位置进行变异,改变了完全随机的变异方式,为算法提供局部深度的搜索以及跳出局部最优;为增强算法的全局探索能力,对适应度值差的粒子进行动态变异,以此达到增大种群潜在搜索空间的目的。最后通过高维的benchmark函数测试改进算法性能。通过仿真结果对比,表明改进算法能有效防止早熟问题,对于多模态函数的优化能够很好地跳出局部极值点,收敛性和收敛精度等方面得到大幅度提升。In order to overcome the premature convergence of PSO algorithm, this paper developed a new PSO algorithm based on subswarm mutation. This paper proposed the subswarm with random directional vibrating exploit to mutate the global optimal site of the swarm, and it changed the way of random mutation. The mutation based on subswarm enabled the algorithm had excellent local exploit ability and circumvented the premature convergence. It used another mutation on bad particles to enhance the algorithm＇ s global exploit ability, and to expand the searching space. It used high dimension benchmark functions to test the performance of it. The results of comparisons show that the proposed algorithm effectively overcomes the premature convergence and shows better global convergence than other improved algorithms and the optimization of multimodal functions is excellent.

关 键 词：早熟收敛 粒子群优化算法 随机定向振荡式搜索 子群 变异 多模态函数优化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]