Partially Random Learning Particle Swarm Optimization with Parameter Adaptation

A modified particle swarm optimization (PSO) with new parameter learning strategy is presented. During the running time, the inertial weight is adaptively adjusted by proportion coefficient. By introducing random learning strategy, the searching scope has been extended to avoid plunging into the local minimum. When the optimum information of the swarm is stagnant, random interfere is added to maintain the optimize ability. The experiment results show that the new algorithm can greatly improve the global convergence ability and enhance the rate of convergence