Analytical and empirical study of particle swarm optimization with a sigmoid decreasing inertia weight

Abstract

The particle swarm optimization (PSO) is an algorithm for finding optimal regions of complex search space through interaction of individuals in a population of particles. Search is conducted by moving particles in the space. Some methods area attempted to improve performance of PSO since is founded, including linearly decreasing inertia weight. The present paper proposes a new variation of PSO model where inertia weight is sigmoid decreasing, called as Sigmoid Decreasing Inertia Weight. Performances of the PSO with a SDIW are studied analytically and empirically. The exploration–exploitation tradeoff is discussed and illustrated, as well. Four different benchmark functions with asymmetric initial range settings are selected as testing functions. The experimental results illustrate the advantage of SDIW that may improve PSO performance significantly.