Plowing PSO: A novel approach to effectively initializing particle swarm optimization

Particle swarm optimization (PSO) is an optimization algorithm that has received much attention in recent years. PSO is a simple and computationally inexpensive algorithm inspired by social behavior of bird flocks and fish schools. However, PSO suffers from premature convergence, especially in high dimensional multimodal functions. To improve PSO performance on global optimization problems, this paper proposes a novel approach, called Plowing PSO algorithm, through introducing a new operator to PSO. The proposed approach combines the exploration ability of random search with the features of PSO. Our approach is validated using ten common complex unimodal/multimodal benchmark functions. The simulation results demonstrate that the proposed approach is superior in avoiding premature convergence to standard PSO, and five variation of it. Therefore, the Plowing PSO algorithm is successful in improving standard PSO to solve complex numerical function optimization problems.