摘要： 探讨类无标度网、全局耦合网、环形网、随机网、星形网等邻域拓扑结构对粒子群优化算法寻优效果的影响。理论分析与实验结果显示，以类无标度网作为邻域拓扑结构的粒子群优化算法在误差范围内的寻优效果最好，收敛速度最快，可以较好地避免陷入局部最优，且网络平均度对粒子群优化算法的寻优效果有一定的影响。

关键词: 粒子群优化算法, 复杂网络, 类无标度网

Abstract: This paper discusses the influence of Scale-Free Like(SFL), GLOBAL, CYCLE, ER and STAR on optimization effect of Particle Swarm Optimization(PSO). Analysis and experimental results show that PSO performs better based on Scale-Free network neighborhood topology than on other neighborhood topologies such as regular network, random network, star network and traditional PSO. A new approach considering Scale-Free network neighborhood topology may be suggested to improve the performance of PSO near the optima and its convergence speed. And mean degree of network has influence on optimization effect of PSO .

Key words: Particle Swarm Optimization(PSO) algorithm, complex network, Scale-Free Like(SFL) network

中图分类号: 

• TP301

• N94