Abstract
This paper proposes Generational Exclusion Particle Swarm Optimization with Central Aggregation Mechanism (GEPSO-CAM) to improve the global searching ability of the standard particle swarm optimization (SPSO). First, in the generational exclusion strategy, particles will not only approach the optimal particle, but also stay away from the worst particle with a certain probability when updating positions. Then, in the central aggregation mechanism, particles learn from both their historical optimal positions and the central positions in the swarm. Finally, the proposed algorithm is compared with SPSO and bacterial foraging optimization (BFO) algorithms based on four benchmark functions. The experimental results show that the GEPSO-CAM can effectively alleviate falling into local optimal solutions and improve the accuracy of optimal solutions.