Particle Swarm Optimization Using Crossover Operator

Particle swarm optimization (PSO) has been widely used mainly due to its simple concept and its ability to converge to reasonable solution fast. However, this algorithm is always inefficient while optimizing complex global optimization problems because it is easy to be trapped into local optima. Researches into the combination of evolutionary operators with PSO is one of the most significant and promising topics to enhance the search ability of PSO. This paper develops a crossover operator and applies it into PSO in order to use all useful information of the swarm to prevent premature convergence. The crossover operator introduces a vector called cBest for each particle, which is used to store the crossover results among all the particles on each dimension. Therefore, the crossover operator utilizes the whole swarm’s information to keep the diversity and guides the particles to the global optimum efficiently. The proposed crossover PSO (CPSO) has been applied to optimize multidimensional mathematical functions, and the experimental results demonstrate that CPSO can prevent the premature and yield better performance when is compared with the traditional PSOs, especially in solving multimodal functions.