A decomposition-based multi-objective Particle Swarm Optimization algorithm for continuous optimization problems

Particle swarm optimization (PSO) is a heuristic optimization technique that uses previous personal best experience and global best experience to search global optimal solutions. This paper studies the application of PSO techniques to multi-objective optimization using decomposition methods. A new decomposition-based multi-objective PSO algorithm is proposed, called MOPSO/D. It integrates PSO into a multiobjective evolutionary algorithm based on decomposition (MOEA/D). The experimental results demonstrate that MOPSO/D can achieve better performance than a well-known MOEA, NSGA-II with differential evolution (DE), on most of the selected test instances. It shows that MOPSO/D will be a competitive candidate for multi-objective optimization.