Dynamic network structured immune particle swarm optimisation with small-world topology

作     者：Sun, Yifei Jiao, Licheng Deng, Xiaozheng Wang, Rongfang 

作者机构：Shanxi Normal Univ Sch Phys & Infomat Technol Xian 710119 Shaanxi Peoples R China Xidian Univ Int Res Ctr Intelligent Percept & Comp Minist Educ Key Lab Intelligent Percept & Image Understanding Xian 710071 Peoples R China 

出 版 物：《INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION》 (国际生物启发计算杂志)

年 卷 期：2017年第9卷第2期

页      面：93-105页

核心收录：

学科分类：0710[理学-生物学] 07[理学] 09[农学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Fundamental Research Funds for the Central Universities [GK201603014] Shaanxi Normal University [JSJX2016Q014] 

主　　题：particle swarm optimisation Newman-Watts small-world model artificial immune system dynamic network structure clonal selection algorithm 

摘      要：Particle swarm optimisation (PSO) has attracted much attention and is used to wide applications in different fields in recent years because of its simple concept, easy implementation and quick convergence. However, it suffers from premature convergence since the population s diversity loses quickly. In this paper, a novel and efficient variant of PSO named DNIPSO is proposed which help the diversity of the swarm be preserved via the Newman-Watts small world network topology and the immune learning operator. Initially the topology of the population is the regular network. Then the Newman-Watts small world topology is formed gradually and the swarm evolves simultaneously. The optimisation process contains the population structure dynamics and particle immune learning two parts which mutually promoted effectively in whole population. Furthermore, the immune operator which is based on the clonal selection theory achieves a trade-off between exploration and exploitation abilities. Numerical experiments both on continuous unconstrained and constrained benchmark functions are used to test the performance of DNIPSO. Simulation results show it is effective and robust.