动态优化环境下的群核进化粒子群优化方法  

Swarm-Core Evolutionary Particle Swarm Optimization in Dynamic Optimization Environments

作　　者：窦全胜[1] 周春光[2] 徐中宇[2] 潘冠宇[2] 

机构地区：[1]山东工商学院信息与电子工程学院,烟台264005 [2]吉林大学计算机科学与技术学院,长春130012

出　　处：《计算机研究与发展》2006年第1期89-95,共7页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60433020);教育部"符号计算与知识工程"重点实验室基金项目

摘　　要：粒子群优化方法是由Kennedy和Eberhart于1995年提出的一种基于群体智能(swarmintelli-gence)的进化计算技术·定义了“群核”(swarm-core)的概念,并在此基础上,提出了基于群核进化的粒子群优化方法(swarm-core evolutionary particle swarmopti mization,SCEPSO),在SCEPSO方法中,为增强群体的优化能力,把群体分成了3个子群体,并且每个子群体有各自不同的“分工”·同时研究了SCEP-SO方法对连续变化的最优点的动态跟踪能力,在3种动态优化模型下进行了实验·实验结果表明,与传统PSO方法相比,SCEPSO方法能够可靠并精确地跟踪连续变化的全局最优解·The particle swarm optimization （PSO） method was originally designed by Kennedy and Eberhart in 1995 and has been applied successfully in various optimization problems. The PSO idea is inspired by natural concepts such as fish schooling, bird flocking and human social relations. The concept of ＂swarm-core＂ is defined in this paper, based on this concept an improved PSO is proposed, which is swarmcore evolutionary particle swarm optimization （SCEPSO） . In order to enhance the optimization power of the swarm, the particle swarm are divided into three sub-swarms and each sub-swarm has different job in SCEPSO. At same time the effectiveness of SCEPSO in tracking changing extrema are investigated, experiments for the three types of dynamic optimization models indicate that the SCEPSO can track a continuously changing solution reliably and accurately compared with PSO.

关 键 词：群体智能 粒子群优化方法 动态优化 群核 子群体 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]