计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (9): 14-17.

• 博士论坛 • 上一篇    下一篇

PSO算法的收敛性及参数选择研究

刘晓峰 陈通   

  1. 天津大学管理学院
  • 收稿日期:2006-11-26 修回日期:1900-01-01 出版日期:2007-03-21 发布日期:2007-03-21
  • 通讯作者: 刘晓峰

Study on The Convergence Analysis and Parameter Choice of Particle Swarm Optimization

  • Received:2006-11-26 Revised:1900-01-01 Online:2007-03-21 Published:2007-03-21

摘要: PSO算法(微粒群算法)是一种仿生优化技术,目前国内外对该算法的研究成果已经很丰富。然而PSO的数学基础还显得相对薄弱,对该算法的研究也仅仅限于在一维问题域内的收敛情况,对二维以及多维算法域收敛稳定性还缺乏深刻且具有普遍意义的理论分析。因此,本文在介绍分析一维问题域算法收敛的基础上,研究PSO算法在二维以及多维算法域内的收敛情况,从而寻求更加有利于微粒群算法收敛的参数选择。

关键词: 微粒群算法, 收敛性研究, 参数选择.

Abstract: Particle Swarm Optimization (PSO) is an optimization algorithm based on population invented by Eberhart and kennedy. Up to this day, there are many articles regarding PSO. However, the systemic and profound research and analysis of convergence of the algorithm is rare, and there are only some limited researches focusing on the convergence of one- dimension –domain problem. Therefore this article aims at studying the convergence of the Particle Swarm Optimization in multiple-dimension–domain problem, looking forward to seeking better parameters to carry out the algorithm.

Key words: Particle Swarm Optimization(PSO), Convergence analysis, Choice of parameters of the algorithm