A particle swarm optimizer for multi-objective optimization

This paper proposes a hybrid particle swarm approach called Simple Multi-Objective Particle Swarm Optimizer (SMOPSO) which incorporates Pareto dominance, an elitist policy, and two techniques to maintain diversity: a mutation operator and a grid which is used as a geographical location over objective function space. In order to validate our approach we use three well-known test functions proposed in the specialized literature. Preliminary simulations results are presented and compared with those obtained with the Pareto Archived Evolution Strategy (PAES) and the Multi-Objective Genetic Algorithm 2 (MOGA2). These results also show that the SMOPSO algorithm is a promising alternative to tackle multi-objective optimization problems. Eje: VI Workshop de Agentes y Sistemas Inteligentes (WASI) Red de Universidades con Carreras en Informática (RedUNCI)