Repulsive Particle Swarm Optimization based on new diversity

To avoid the problem of premature convergence, a new diversity-guided Particle Swarm Optimizer (PSO), namely MARPSO is proposed, which is a modification of attractive and repulsive PSO (ARPSO), suggested by Riget and Vesterstorm. A novel measure of population diversity function is presented and a new concept of the particle´s best flight direction is introduced. The simulation test results of four classic functions show that: compared with Standard PSO (BPSO) and ARPSO, MARPSO can effectively increase the diversity of swarm, while maintain a higher convergence speed.