Two-Subpopulation Particle Swarm Optimization Based on Pheromone Diffusion

Abstract:

The particle swarm optimization (PSO) algorithm is a new population based search strat-egy, which has exhibited good performance on well-known numerical test problems. However, conventional algorithm of particle swarm optimization (PSO) is often trapped in local optima in global optimization of multimodal high-dimensional function. Analysis of the main causes of the premature convergence, proposes an improved two-subpopulation PSO algorithm, based on the mechanism of pheromone diffusion and diversity feedback. The population is divided into main subpopulation particle swarm and assistant subpopulation particle swarm, whose search direction is inversed completely. A pheromone diffusion function, which can control the degree of convergence of particles move to the best position, is designed by both taking into account these particles distribution and their fitness value. Adjusting inertial weight and numbers of sub-populations adaptively with diversity feedback greatly contribute to breaking away from local optima. Experiments on optimization of high-dimension benchmark functions show that, comparing with some other PSO variants, the improved algorithm can find better optima with converges faster, and prevent more effectively the premature convergence.

• Periodical: Applied Mechanics and Materials (Volume 667)
• Pages: 300-308
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.667.300
• Online since: October 2014
• Authors: Guang Pu Zeng*, Hui Lian Fan
• Keywords: Diversity Feedback, Heuristic Methods, Particle Swarm Optimization (PSO), Pheromone Diffusion

References

[1] KENNEDY J, EBERHART R C. Particle swarm optimization[C]/ Proceedings of IEEE International Conference on Neural Networks. Perth: IEEE Press, 1995: 1942 - (1948).

[2] WANG Hong-feng, WANG Ding-wei, HUANG Min. Forking PSO Algorithm for Dynamic Optimization Problems[J]. Journal of System Simulation, 2010，22（12）：2895-2899.

[3] ZHANG, JIAJUN. A novel particle swarm optimization for image fusion[C]/ 2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics, March 6-7, 2010, Wuhan, China: IEEE Computer Society Press, 2010: 126-129.

DOI: 10.1109/car.2010.5456644

[4] HAN Li, XIN Mao, LUO Ci-yong. Design of permanent magnet direct current motors based on a particle swarm optimization algorithm[J], Journal of Chongqing University(Natural Science Edition), 2009, 32 （5）：535-538.

[5] KIM TAE-HYOUNG, ICHIRO MARUTA, TOSHIHARU SUGIE. Robust PID controller tuning based on the constrained particle swarm optimization[J]. Automatica, 2008, 44(4): 1104-1110.

DOI: 10.1109/cdc.2007.4434126

[6] ZHU JINRONG. A modified particle swarm optimization algorithm[J]. Journal of Computers, 2009, 4(12): 1234-1236.

[7] Kennedy J, Mendes R. Population structure and particle swarm performance[C]/Proceedings of IEEE Conference on the CEC 2002, Honolulu: IEEE Press, 2002: 1671−1676.

[8] LIANG JJ, QIN AK. Comprehensive learning particle swarm optimizer for global optimization of multimodal functions[C]/Proceedings of IEEE Conference on Evolutionary Computation, Singapore: IEEE Press, 2006: 281−295.

DOI: 10.1109/tevc.2005.857610

[9] YAO Jin-tao, ZHU Sheng-lin, ZHOU Min, etc. Particle Swarm Optimization with Predatory Escape Behavior[J]. Journal of System Simulation, 2010, 22(5): 1151-1154.

[10] J. Branke, T. Kaußler, C. Schmidth, and H. Schmeck. A multi-population approach to dynamic optimization problems. Proc. 4th Int. Conf. on Adaptive Computing in Design and Manufacturing, pp.299-308, (2000).

[11] D. Parrott and X. Li. A particle swarm model for track-ing multiple peaks in a dynamic environment using speciation. Proc. of the 2004 IEEE Congress on Evo-lutionary Computation, pp.98-103, (2004).

DOI: 10.1109/cec.2004.1330843

[12] T. M. Blackwell and J. Branke. Multi-swarm opti-mization in dynamic environments. In G. R. Raidl, ed-itor, Applications of Evolutionary Computing, LNCS 3005, pp.489-500, (2004).

DOI: 10.1007/978-3-540-24653-4_50

[13] T. M. Blackwell and J. Branke. Multiswarms, ex-clusion, and anti-convergence in dynamic environ-ments. IEEE Transactions on Evolutionary Computa-tion, 10(4): 459-472, (2006).

DOI: 10.1109/tevc.2005.857074

[14] J. Branke. Memory enhanced evolutionary algorithms for changing optimization problems. Proc. of the 1999 Congr. on Evol. Comput., vol. 3, pp.1875-1882, (1999).

[15] HE Ran, WANG Yong-Ji, WANG Qing, etc. An Improved Particle Swarm Optimization Based on Self-Adaptive Escape Velocity [J]. Journal of Software , 2005, 16(12): 2036-(2043).

DOI: 10.1360/jos162036