The hybridized equilibrium and particle swarm optimization algorithms

Abstract

Along with the development of nature inspired swarm-based algorithms, the individuals involved in updating their positions in swarms have changed from their average, to the historical best candidates, the best candidates and random selected candidates. The averages have been abandoned by now. However, only the individuals in particle swarm optimization (PSO) algorithm embraced the historical trajectories. In this paper, the newly proposed algorithm called the equilibrium optimization (EO) algorithm was improved with the hybridization of the PSO algorithm, the historical trajectories of individuals would play the role in updating the concentrations of individuals in EO swarms. Simulation experiments were carried and the final results verified the better performance of the improved hybridization.