A Novel Particle Swarm Optimization Algorithm Based on Fuzzy Velocity Updating for Multi-objective Optimization

A novel particle swarm optimization algorithm for multi-objective optimization (MOO) based on fuzzy velocity updating strategy is developed and implemented in this paper. The proposed algorithm incorporates fuzzy velocity updating strategy, which can characterize to some extent the uncertainty on the true optimality of the global best position, into particle swarm optimization (PSO) so as to avoid the premature convergence and to maintain the swarm diversity. In addition, a crowding distance computation operator for promoting solution diversity and an efficient mutation operator for searching feasible non-dominated solutions are adopted. The proposed algorithm is tested on various benchmark problems taken from the literature and evaluated with standard performance metrics by comparison with NSGA-II. It is found that the proposed algorithm does not have any difficulties in achieving well-spread Pareto optimal solutions with good convergence to true Pareto optimal front.