A modified particle swarm optimizer with roulette selection operator

In this paper, a novel particle swarm optimizer combined with the roulette selection operator is proposed, which provides a mechanism to restrain the predominating of super particles in early stage and can effectively avoid the premature problem. We conduct variety experiments to test the proposed algorithm and compare it with other published methods on several test functions taken from the literature. The computational results demonstrate that this revised algorithm is promising to achieve faster convergence and better solutions, especially for multimodal function optimization.