A diversity-guided hybrid particle swarm optimization based on gradient search

As an evolutionary computing technique, particle swarm optimization (PSO) has good global search ability, but it is easy to make the swarm lose its diversity and lead to premature convergence. In this paper, a diversity-guided hybrid PSO based on gradient search is proposed to improve the search ability of the swarm. The adaptive PSO is first used to search the solution till the swarm loses its diversity. Then, the search process turns to a new PSO (DGPSOGS), and the particles update their velocities with their gradient directions as well as repel each other to improve the swarm diversity. Depending on the diversity value of the swarm, the proposed hybrid method switches alternately between two PSOs. The hybrid algorithm adaptively searches local minima with random search realized by adaptive PSO and performs global search with semi-deterministic search realized by DGPSOGS, and so its search ability is improved. The experimental results show that the proposed hybrid algorithm has better convergence performance with better diversity compared to some classical PSOs.