Gaussion Mutation Particle Swarm Optimization with Dynamic Adaptation Inertia Weight

Abstract

An improved PSO with decreasing inertia weight is proposed in this paper, which is different from the inertia weight of standard PSO. In addition, a new social component instead of the old one to make more explore and a tiny Gauss perturbation joined in the position equation to help maintain swarm diversity. Four standard test functions with asymmetric initial range settings are used to prove its validity. Experimental results verify its superiority both in convergent speed and solution precision. Conclusions are drawn in the end