The Research On Particle Swarm Optimization Algorithm For Multi-Objective Optimization

Multi-objective optimization problem (MOP) is one of the most important research areas in optimization method and MOP has great value in real-world applications. But traditional methods have many restrictions to solve MOP, so multi-objective evolutionary algorithms (MOEAs) have great developments to solve MOP in last decades, some attempts in this area have been made with significant results such as NSGA2, SPEA2 and so on.Kennedy and Eberhart presented a new optimization method named Particle Swarm Optimization (PSO) in 1995 which is inspired by the flocking and swarm behavior of birds, insects, and fish schools. PSO is simple and efficient, so many researchers have been attracted by this algorithm, and furthermore, it converges fast by moving each particle aimed at guides when it deals with single- objective optimization, and these features are important in multi-objective optimization also. From some current research works,we describe a multi-objective particle swarm optimization algorithm (MOPSO) that incorporates the concept of the enhancedε-dominance, we present this new concept to update the archive, the archiving technique can help us to maintain a sequence of well-spread solutions. A new particle update strategy and the mutation operator are shown to speed up convergence. To compare with the state-of-art MOEAs and some well known MOPSO techniques on a well-established suite of test problems, our new approach is simple constructed, and results indicate that it works effective and has steady-state performance. It is confirmed from the results that the proposed method outperforms other methods.