一种新的自适应小生境粒子群优化算法  

Cooperative Evolutionary Quantum Particle Swarm Optimization Algorithm with Multi-Populations

作　　者：宋书强[1] 叶春明[1] 

机构地区：[1]上海理工大学管理学院,上海200093

出　　处：《计算机仿真》2010年第10期175-178,258,共5页Computer Simulation

基　　金：上海市重点学科建设项目(S30504);上海市研究生创新基金项目(JWCXSL0802)

摘　　要：为了克服基本粒子群算法过早收敛的缺陷,提出了一种新的自适应小生境粒子群优化算法。首先,让整个粒子群进行独立地演化寻优,以构造小生境环境。同时,通过设定合适的信息共享周期,以实现各个粒子搜索信息的共享,指导粒子向全局最优位置的搜索。最后,通过几个典型的多峰测试函数,对算法进行了仿真验证。结果表明,在算法的收敛性、寻优性等方面,算法均达到了良好的效果。In order to overcome the shortcoming that the PSO algorithm is easy to be trapped into local minima,A new auto-adapted niche PSO algorithm is presented based on the analysis of the basic PSO.First,In the whole particle swarm group,every subgroups evolved independently by constructing the niche environment,and updated sharing information periodically for the best position.Finally we use several practical analyses to confirm the performance of the method.The results show that AN-PSO is effective in solving the problem.The results of simulation indicate that AN-PSO perform better than PSO algorithms.

关 键 词：粒子群算法 小生境 自适应 多峰函数 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]