Particle Swarm Optimization with Average Individuals Distance‐Incorporated Exploitation

Abstract

Particle swarm optimization (PSO) is a popular optimization technique known for its simplicity and effectiveness. This paper introduces a variant that achieves a better balance between exploration and exploitation, named DiPSO. DiPSO incorporates a novel strategy based on trends in mean distance between individuals for local exploitation control. Experiments on 29 benchmark functions demonstrate that DiPSO consistently outperforms the state‐of‐the‐art variant of PSO. Convergence analysis reveals that DiPSO achieves faster convergence and superior solutions. These results highlight the effectiveness of DiPSO in solving optimization problems. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.