An Adaptive Convergence Speed Controller Framework for Particle Swarm Optimization Variants in Single Objective Optimization Problems

Particle swarm optimization (PSO) has been shown as an effective tool for solving single objective optimization problems. However, premature convergence is the major obstacle for PSO. So far, many PSO variants have been proposed to prevent premature convergence. Nonetheless, even though some strategies have been adopted for avoiding premature convergence, PSO variants could not achieve all great performance. In this paper, we introduce an adaptive general framework to enhance the performance of PSO variants, convergence speed controller with an adaptive diversity control strategy (CSC-ADCS). With the aim to maintain the convergence speed and prevent premature convergence, CSC will conditionally detect the status of Swarm. And ADCS is introduced so that the conditions are adaptive on the basis of the diversity of swarm. Once the CSC framework detects that premature convergence occurs, two rules would help the swarm to get rid of the abnormal status. The experimental results conducted on CEC'2013 benchmark functions show that with the help of adaptive CSC framework, PSO variants with CSC-ADCS will get better results than ones without CSC-ADCS.