A novel particle swarm optimisation algorithm for continuous function optimisation

Particle swarm optimisation (PSO) algorithms are applied in a variety of fields. A good quality solution for a problem depends on the PSO parameters chosen for the problem under study. In this paper, a continuous particle swarm optimisation algorithm is proposed to solve the unconstrained optimisation problems. This paper proposes a novel and simple variation of the PSO algorithm by introducing dynamic updating of velocity without any parameters, such as inertia weight and constriction coefficients that are commonly used in the traditional PSO algorithms. The proposed algorithm is applied to well‐known benchmark functions which are commonly used to test the performance of numeric optimisation algorithms, and the results are compared with the existing PSO algorithms. It is found that the proposed algorithm gives superior results in terms of speed of convergence and the ability of finding the solutions of excellent quality.