计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (3): 51-54.DOI: 10.3778/j.issn.1002-8331.2009.03.014

• 研究、探讨 • 上一篇    下一篇

多粒子群协同进化算法

许 珂1,刘 栋2   

  1. 1.德州学院 计算机系,山东 德州 253000
    2.山东师范大学 信息科学与工程学院,济南 250014
  • 收稿日期:2008-01-08 修回日期:2008-04-02 出版日期:2009-01-21 发布日期:2009-01-21
  • 通讯作者: 许 珂

Algorithm of multi-PSO co-evolution based on GA and PSO

XU Ke1,LIU Dong2   

  1. 1.Department of Computer Science & Technology,Dezhou University,Dezhou,Shandong 253000,China
    2.School of Information Science and Engineering,Shandong Normal University,Jinan 250014,China
  • Received:2008-01-08 Revised:2008-04-02 Online:2009-01-21 Published:2009-01-21
  • Contact: XU Ke

摘要: 针对遗传算法收敛速度慢且易于陷入局部最优,而微粒群算法存在早熟的现象,提出了一种多粒子群协同进化算法,在多个粒子群协同进化的同时,通过构建基因库,使较劣的粒子根据基因库进行遗传操作,用4个基准函数进行实验表明,算法MPSOE3性能明显优于基本PSO算法,最后对该算法进行了推广,给出了一种基于计算智能的多群协同进化模型。

关键词: 遗传算法, 粒子群优化, 协同进化, 多种群

Abstract: Firstly introduced genetic algorithms and particle swarm optimization algorithms,based on which an algorithm of multi-pso co-evolution is proposed.Four benchmark function are tested and shown that the performance of the MPSOE3 algorithm is better than basic PSO algorithm.Lastly extended the algorithm and given a model of multi-swarm co-evolution,which is based on computational intelligence.

Key words: genetic algorithms, Particle Swarm Optimization(PSO), co-evolution, multi-swarm