A composite particle swarm algorithm for global optimization of multimodal functions

Abstract

During the last decade, many variants of the original particle swarm optimization (PSO) algorithm have been proposed for global numerical optimization, but they usually face many challenges such as low solution quality and slow convergence speed on multimodal function optimization. A composite particle swarm optimization (CPSO) for solving these difficulties is presented, in which a novel learning strategy plus an assisted search mechanism framework is used. Instead of simple learning strategy of the original PSO, the proposed CPSO combines one particle’s historical best information and the global best information into one learning exemplar to guide the particle movement. The proposed learning strategy can reserve the original search information and lead to faster convergence speed. The proposed assisted search mechanism is designed to look for the global optimum. Search direction of particles can be greatly changed by this mechanism so that the algorithm has a large chance to escape from local optima. In order to make the assisted search mechanism more efficient and the algorithm more reliable, the executive probability of the assisted search mechanism is adjusted by the feedback of the improvement degree of optimal value after each iteration. According to the result of numerical experiments on multimodal benchmark functions such as Schwefel, Rastrigin, Ackley and Griewank both with and without coordinate rotation, the proposed CPSO offers faster convergence speed, higher quality solution and stronger robustness than other variants of PSO.

Keywords

particle swarm algorithm / global numerical optimization / novel learning strategy / assisted search mechanism / feedback probability regulation

References

[1] CorneD, DorigoM, GloverFNew ideas in optimization [M], 1999, USA, McGraw-Hill: 34-36

[2] HorstR, PardalosP M, ThoaiN VIntroduction to global optimization. Dordrecht [M], 2000, Netherland, Kluwer Academic Publishers: 67-68

[3] KennedyJ, EberhartR. Particle swarm optimization [C]. IEEE international conference on neural networks, 1995, Australia, IEEE Press: 1942-1948

[4] MendesR, KennedyJ, NevesJ. The fully informed particle swarm: Simpler, maybe better [J]. IEEE Transaction on Evolutionary Computation, 2004, 8(3): 204-210

[5] LingJ J, QinA K, SuganthanP N, BaskarS. Comprehensive learning particle swarm optimizer for global optimization of multimodal functions [J]. IEEE Transaction on Evolutionary Computation, 2006, 10(3): 281-295

[6] ZhanZ H, ZhangJ, LiY, ShiY H. Orthogonal learning particle swarm optimization [J]. IEEE Transaction on Evolutionary Computation, 2011, 15(6): 832-847

[7] WangY, LiB, WeiseT, WangJ Y, YuanB, TianQ J. Self-adaptive learning based particle swarm optimization [J]. Information Sciences, 2011, 18(120): 4514-4538

[8] KennedyJ, MendesR. Population structure and particle swarm performance [C]. IEEE international conference on evolutionary computation, 2002, Hawaii, US, IEEE Press: 1671-1676

[9] SuganthanP N. Particle swarm optimizer with neighborhood operator [C]. IEEE international conference on evolutionary computation, 1999, Washington DC, US, IEEE Press: 1958-1962

[10] HuX, EberhartR C. Multiobjective optimization using dynamic neighborhood operator [C]. IEEE international conference on evolutionary computation, 2002, Hawaii, US, IEEE Press: 1677-1681

[11] JansonS, MiddendorfM. A hierarchical particle swarm optimizer for dynamic optimization problems [J]. Applications of Evolutionary Computing, 2004513-523

[12] ShiY, LiuH C, GaoL, ZhangG H. Cellular particle swarm optimization [J]. Information Sciences, 2011, 18(120): 4460-4493

[13] SunJ, FangW, PaladeV, WuX J, XuW B. Quantum-behaved particle swarm optimization with Gaussian distributed local attractor point [J]. Applied Mathematics and Computation, 2011, 21(87): 3763-3765

[14] ShiX H, LiY W, LiH J, GuanR C, WangL P, LiangY C. An integrated algorithm based on artificial bee colony and particle swarm optimization [C]. 6th international conference on neural computation, 2010, Changchun, China, IEEE Press: 2586-2590

[15] WangF, HeX S, LuoL G, WangY. Hybrid optimization algorithm of PSO and Cuckoo Search [C]. International conference on artificial intelligence. management science and electronic, 2011, Xi’an, China, IEEE Press: 1172-1175

[16] ZhouX-c, ZhaoZ-x, ZhouK-j, HeC-hong. Remanufacturing closed-loop supply chain network design based on genetic particle swarm optimization algorithm [J]. Journal of Central South University: Science and Technology, 2012, 19: 482-487

[17] MONTES De OcaM A, StutzleT, BirattariM, DorigoM. Frankenstein’s PSO: A composite particle swarm optimization algorithm [J]. IEEE Transaction on Evolutionary Computation, 2009, 13(5): 1120-1132

[18] ParsopoulosK E, VrahatisM N. On the computation of all global minimizers through particle swarm optimization [J]. IEEE Transaction on Evolutionary Computation, 2004, 8(3): 211-224

[19] van Den BerghF, EngelbrechtA P. A cooperative approach to particle swarm optimization [J]. IEEE Transaction on Evolutionary Computation, 2004, 8(3): 225-239

[20] ShiY, EberhartR. A Modified Particle Swarm Optimizer [C]. IEEE international conference on evolutionary computation, 1999, Washington DC, US, IEEE Press: 69-73

[21] MauriceC, KennedyJ. The particle swarm-explosion, stability, and convergence in a multidimensional complex space [J]. IEEE Transaction on Evolutionary Computation, 2002, 6(1): 58-73

[22] ParsopoulosK E, VrahatisM N. UPSO-A unified particle swarm optimization scheme [C]. Proceedings of the International Conference of Computational Methods in Sciences and Engineering, 2004, Attica, VSP Science Publishers: 868-873