A New Improved Simplified Particle Swarm Optimization Algorithm

Abstract

A new simplified particle swarm optimization algorithm is proposed for the question that the basic particle swarm optimization algorithm is easy to fall into the local optima. The algorithm introduces new parameters on the basis of simplifying particle swarm, adjusts parameters by adaptive method, and coordinates the relationship between various parameters, which increases the use of particle information and ensures the difference between particles. Through the test function of eight, the improved algorithm can effectively avoid the premature convergence and greatly improve the convergence speed and convergence precision.