Authors: Dazhi Jiang; Sanyou Zeng; Hui Wang; Zhijian Wu
Addresses: Department of Computer Science, Shantou University, Shantou 515063, China. ' School of Computer Science, China University of Geosciences, Wuhan 430074, China. ' The State Key Laboratory of Software Engineering, Wuhan University, Wuhan 430072, China. ' The State Key Laboratory of Software Engineering, Wuhan University, Wuhan 430072, China
Abstract: Particle swarm optimiser (PSO) has shown good performance in lots of optimisation problems. However, it easily suffers from premature convergence when solving complex optimisation problems. In order to improve the performance of PSO, this paper presents an enhanced evolutionary algorithm named as PSO with hybrid multi-parent crossover and discrete recombination (PSOHMCDR), which is based on the characteristics of PSO, multi-parent crossover algorithm and differential evolution (DE). Experimental results show that PSOHMCDR outperforms other nine algorithms, including six PSO variants and three typical and effective DE variants.
Keywords: particle swarm optimisation; PSO; multi-parent crossover; differential evolution; discrete recombination; enhanced evolutionary algorithms.
International Journal of Intelligent Information and Database Systems, 2011 Vol.5 No.6, pp.597 - 617
Available online: 17 Oct 2011 *Full-text access for editors Access for subscribers Purchase this article Comment on this article