计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (8): 40-44.DOI: 10.3778/j.issn.1002-8331.2010.08.012

• 研究、探讨 • 上一篇    下一篇

基于聚类分析的随机微粒群算法

郝武伟1,曾建潮2   

  1. 1.山西交通职业技术学院 经济管理系,太原 030031
    2.太原科技大学 系统仿真与计算机应用研究所,太原 030024
  • 收稿日期:2009-03-12 修回日期:2009-05-11 出版日期:2010-03-11 发布日期:2010-03-11
  • 通讯作者: 郝武伟

Stochastic particle swarm optimization algorithm based on cluster analysis

HAO Wu-wei1,ZENG Jian-chao2   

  1. 1.Department of Economics and Management,Shanxi Communications Polytechnic,Taiyuan 030031,China
    2.Division of System Simulation and Computer Application,Taiyuan University of Science and Technology,Taiyuan 030024,China
  • Received:2009-03-12 Revised:2009-05-11 Online:2010-03-11 Published:2010-03-11
  • Contact: HAO Wu-wei

摘要: 在对一种保证全局收敛的微粒群算法——随机PSO算法(SPSO)进行分析的基础上,提出了一种基于聚类分析的随机微粒群算法(CSPSO)。CSPSO算法保证了种群的多样性,使微粒能够有效地进行全局搜索。并证明了它依概率收敛于全局最优解。最后以典型的复杂基准优化问题进行了仿真实验,验证了CSPSO的有效性。

Abstract: A new Stochastic Particle Swarm Optimization algorithm based on Cluster analysis(CSPSO) is proposed based on the analysis of Stochastic Particle Swarm Optimization algorithm(SPSO) that guarantees global convergence.The CSPSO is guaranteed that the particles are diversiform,and can make particles explore the global optimization more efficiently.The CSPSO is guaranteed to converge to the global optimization solution with probability one.Finally,several complex examples are simulated to show that CSPSO is more efficient than SPSO.

中图分类号: