A novel multi-objective decomposition particle swarm optimization based on comprehensive learning strategy

Abstract

Comprehensive learning particle swarm optimization (CLPSO) algorithm has a good performance in overcoming premature convergence and avoiding getting stuck in local minima, which are shortcomings in particle swarm optimization. It can solve complex, multi-modal of single-objective problems, but it has not such performance in handling multi-objective optimization problems because of the difficulty of selective solution mechanism. In this article, a multi-objective decomposition particle swarm optimization based on comprehensive learning strategy is proposed, which uses a comprehensive learning strategy for multi-objective problems to prevent premature convergence; updates the leading particles by decomposition method to enhance the distribution of solutions; adds the archive to preserve non-dominated solutions, and adopts mutation in archive to avoid falling into local optimum. The proposed approach is compared with three multi-objective evolutionary algorithms and the results indicate that the proposed approach is competitive respect to which it is compared in most of the test problems adopted.