Abstract
In this work, a modified version of the newly-developed algorithm Improved Particle Swarm Optimization (PSOI) is proposed. PSOI is a type of a PSO algorithm that uses time-varying social coefficients to train the particles. It shows a better performance compared to the conventional PSO, and this inspires this work. The proposed method uses asymmetric polynomial curves, and hence, it is referred to as the Improved Asymmetric PSO (PSOAI). In this work, PSOAI is tested using several benchmarks and compared to several PSO versions including the PSOI. The results are promising compared to several versions of PSO.