Particle Swarm Optimization via Successive Optimization in Its Parameter Space

Abstract

In this paper, we propose a new Particle Swarm Optimization (PSO), which is based on successive optimization in its parameter space, in order to overcome the difficulty for applying PSO to complex and high dimensional nonlinear optimization problems. The proposed PSO consists of two types of optimization procedures; optimization in its decision variable space and optimization in its parameter space. Some numerical simulations using six types of typical benchmark problems verify the performance of the proposed PSO.