Space-based initialization strategy for particle swarm optimization

Abstract

Particle Swarm Optimization (PSO) is a population-based stochastic optimization algorithm that has been applied to various scientific and engineering problems. Despite its fast convergence speed, the original PSO is easy to fall into local optima when solving multi-modal functions. To address this problem, we present a novel initialization strategy, namely Space-based Initialization Strategy (SIS), to help PSO avoid local optima. We embed SIS into the standard PSO and form a novel PSO variant named SIS-PSO. The performance of SIS-PSO is validated by 13 benchmark functions and the experimental results demonstrate that the SIS enables PSO to achieve faster convergence speed and higher solution accuracy especially in multi-modal problems.