An Effective Particle Swarm Optimization for Global Optimization Computational Intelligence and Intelligent Systems
edited by: Zhenhua Li, Xiang Li, Yong Liu, Zhihua Cai
In this paper, a novel chaotic particle swarm optimization with nonlinear time varying acceleration coefficient is introduced. The proposed modified particle swarm optimization algorithm (MPSO) greatly elevates global and local search abilities and overcomes the premature convergence of the original algorithm. This study aims to investigate the performance of the new algorithm, as an effective global optimization method, on a suite of some well-known benchmark functions and provides comparisons with the standard version of the algorithm. The simulated results illustrate that the proposed MPSO has the potential to converge faster, while improving the quality of solution. Experimental results confirm superior performance of the new method compared with standard PSO.