基于k-均值的自适应PSO优化算法  

Self-adaptive PSO Algorithm Based on k- mean Clustering

作　　者：刘淳安[1] 

机构地区：[1]宝鸡文理学院计算与信息科学研究所,陕西宝鸡721013

出　　处：《海南大学学报（自然科学版）》2008年第2期179-182,共4页Natural Science Journal of Hainan University

基　　金：陕西省自然科学基础研究计划项目(2006A12);陕西省教育厅科学研究计划项目(07JK180);宝鸡文理学院重点科研项目(ZK0619)

摘　　要：提出了一种新的基于k-均值聚类的自适应PSO优化算法(KCMPSO).首先通过k-均值聚类方法把粒子群分成若干个子群体,从而在迭代过程中每个粒子根据其个体极值和所在子群体中的最好个体更新自己的位置和速度,其次引入自适应变异算子,有效地增强了粒子群之间信息交换和PSO算法跳出局部最优解的能力.几个典型函数的测试结果表明,该算法是非常有效的.A new self-adaptive panicle swarm optimization algorithm （KCMPSO） based on k-mean clustering is presented in the paper. First, the panicle swarm is divided into several sub-populations by the k-mean clustering. And then, the current panicles are updated by the personal best panicle and global best panicles in the sub-populations. Second, by the self-adaptive mutation operator introduced to the algorithm, the information exchanged between different sub-populations and the ability of PSO algorithm broke away from the local optimum are effectively improved. The computer simulations demonstrate the proposed algorithm is very effective.

关 键 词：PSO优化算法 K-均值聚类 自适应变异 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP18[自动化与计算机技术—计算机科学与技术]