Hybrid Particle Swarm Optimizers with a General Fitness Evaluation Strategy

The particle swarm optimization (PSO) is a stochastic population-based optimization technique, which is gaining popularity but may cause premature convergence, especially for multimodal and high-dimensional function optimization. The general fitness evaluation strategy (GFES) is a novel strategy proposed most recently, by which a particle is evaluated in multiple subspaces so as to take diverse paces toward the destination position. This paper hybridizes GFES with several PSO´s variants. Experiments are conducted on some benchmark optimization problems. The results show that these hybrid PSOs are effective for coping with multimodal problems.