Comparing with Chaotic Inertia Weights in Particle Swarm Optimization

The inertia weight is one of the parameter in particle swarm optimization algorithm. It gets important effect on balancing the global search and the local search in PSO. Basing on the linear descending inertia weight and the random inertia weight, this paper presents the strategy of chaotic descending inertia weight and the strategy of chaotic random inertia weight by introduced chaotic optimization mechanism into PSO algorithm. They make PSO algorithm has the characteristics of preferable convergence precision, quickly convergence velocity and better global search ability. The PSO using the chaotic random inertia weight performs especial outstanding comparing with the PSO using random inertia weight, owing to it has rough search stage and minute search stage alternately in all its evolutionary process. The chaotic inertia weight PSO using logistic mapping performs little better than that using tent mapping.