Research on Improvement of Particle Swarm Optimization

Although the particle swarm optimization algorithm has simple principle, few parameters and easy implementation, the particle swarm optimization algorithm is easy to fall into local optimum on multi-mode function and the local search ability is relatively weak. In this paper, the improvement of these two defects is carried out. The particle motion formula with learning model is added, and the generation strategy of a guided vector is added to improve the particle swarm optimization algorithm. The improved algorithm has a two-layer structure, and finally the research direction is prospected.

[1]  Xiao-Feng Xie,et al.  DEPSO: hybrid particle swarm with differential evolution operator , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[2]  Meng Zhang,et al.  Chaotic co-evolutionary algorithm based on differential evolution and particle swarm optimization , 2009, 2009 IEEE International Conference on Automation and Logistics.

[3]  Patrick Siarry,et al.  An adaptive multiobjective particle swarm optimization algorithm , 2011 .

[4]  Jianhong Zhou,et al.  An opposition-based learning competitive particle swarm optimizer , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[5]  Ganesh K. Venayagamoorthy,et al.  Evolving Digital Circuits Using Hybrid Particle Swarm Optimization and Differential Evolution , 2006, Int. J. Neural Syst..

[6]  Hui Wang,et al.  Diversity enhanced particle swarm optimization with neighborhood search , 2013, Inf. Sci..

[7]  Athanasios V. Vasilakos,et al.  Vector coevolving particle swarm optimization algorithm , 2017, Inf. Sci..

[8]  Michael G. Epitropakis,et al.  Evolving cognitive and social experience in Particle Swarm Optimization through Differential Evolution: A hybrid approach , 2012, Inf. Sci..

[9]  Yu Wang,et al.  Self-adaptive learning based particle swarm optimization , 2011, Inf. Sci..