期刊名称：Journal of Software Engineering and Applications
印刷版ISSN：1945-3116
电子版ISSN：1945-3124
出版年度：2017
卷号：10
期号：02
页码：143-158
DOI：10.4236/jsea.2017.102008
语种：English
出版社：Scientific Research Publishing
摘要：TCPSO (Two-swarm Cooperative Particle Swarm Optimization) has been proposed by Sun and Li in 2014. TCPSO divides the swarms into two groups with different migration rules, and it has higher performance for high-dimensional nonlinear optimization problems than traditional PSO and other modified method of PSO. This paper proposes a particle swarm optimization by modifying TCPSO to avoid inappropriate convergence onto local optima. The quite feature of the proposed method is that two kinds of subpopulations constructed based on the scheme of TCPSO are divided into some clusters based on distance measure, k-means clustering method, to maintain both diversity and centralization of search process are maintained. This paper conducts numerical experiments using several types of functions, and the experimental results indicate that the proposed method has higher performance than the TCPSO for large-scale optimization problems.
