An efficient improved particle swarm optimization based on prey behavior of fish schooling

Particle swarm optimization (PSO) is a population based optimization technique to search approximate solutions for extremely difficult or impossible numeric problems. However, PSO may easily get trapped in a local optimum when solving complex multimodal problems. This paper proposes an efficient improved PSO based on prey behavior of fish schooling (FSPSO). Firstly, the fish find better place to prey according to the heuristic water wave which other fish provide, and the heuristic information can be used to enhance the global search ability in PSO. Therefore, the global best particle searches randomly towards several best positions that other particles have experienced. Secondly, the weak fish that cannot move quickly are eaten when the fish schooling are attacked. The decimation of the weak fish can be simulated in PSO to avoid the local optimum and to increase the diversity of the population. Hence, the particles in the immediate vicinity of the global worst particle are replaced by new particles. Finally, the proposed FSPSO is tested on both several standard benchmark functions and a typical NP-complete problem. The results demonstrate that our algorithm achieves remarkable improvements over the basic PSO and even other improved PSOs.