摘要
通过两组搜索方向相反、相互协同的主、辅子群,构造一种新的双子群粒子群优化算法.该算法扩展了种群的搜索范围,充分利用搜索域内的有用信息,在感知到环境变化时能迅速、准确地跟踪动态变化的极值.使用DF1(Dynamic Function 1)生成的复杂动态环境对该算法进行了验证,并与Eberhart提出的动态环境下的粒子群优化算法进行了比较分析.仿真结果表明了该算法的有效性.
Through main subpopulation particle swarm and assistant subpopulation particle swarm, whose searching direction are inversed completely, a two-subpopulation particle swarm optimization algorithm is proposed, which extends the searching rang. Changing extrema can be tracked promptly and accurately when the variable envrionment is detected. The simulative environment used in these experiments is generated by DF1 （Dynamic Function 1）, and the results show that the improved PSO algorithm is more effective and adaptive than the PSO algorithm proposed by Eberhart.
出处
《控制与决策》
EI
CSCD
北大核心
2009年第7期1083-1086,1091,共5页
Control and Decision
关键词
粒子群优化
动态环境
子群
PSO
Dynamic environment
Subpopulation
