Variants of particle swarm optimization and onus of acceleration coefficients

Abstract

The Particle Swarm Optimization (PSO) is a widely used optimization algorithm for finding optimized solutions in a diverse gamut of problem domains. The parameters like Initialization, Constriction factor, Inertia Weight, Mutation Operator, Fuzzy Logic and Parallelism have engendered the Particle Swarm Optimization (PSO) with many variants. The variants of PSO have outperformed the Basic Particle Swarm Optimization. In order to comprehend the role of acceleration coefficients in BPSO, an inquiry is carried out. It is observed that the convergence speed of the BPSO is quicker when the acceleration coefficients are not equal than when both are equal.