A multiple subswarms evolutionary algorithm for multi-objective optimization problems

A new MOPSO algorithm is proposed, which divides a evolutionary swarm into several subswarms based on trait of MOP and uses Pareto dominance concepts to construct the globally optimal region. The region guides the evolutionary of whole particle swarm. By the exchange informations among the particles, the whole particle swarm distributes uniformly and avoides local optimum, and the diversity of the solution is ensured. The uniformly distributed Pareto optimal set is obtained by a few iterations. Numerical simulations show the effectiveness of the proposed algorithm.