Particle swarm optimisation with modified global search and local search exemplars for large-scale optimisation
Minchong Chen, Hongye Li, Qi Yu, Xuejing Hou
Abstract
Canonical particle swarm optimisation (cPSO) has been criticised for its premature convergence when tackling large-scale optimisation problems (LSOPs). During optimisation, the swarm diversity of cPSO rapidly decays, leading to its poor global search performance. To improve the global search ability of cPSO, a particle swarm optimisation with modified global search and local search exemplars (PSO-MGLE) is proposed. In PSO-MGLE, two novel exemplar selection strategies are designed to diversify the selection of global search and local search exemplars for updated particles, thereby preserving high swarm diversity. Second, a dynamic adjustment strategy for the acceleration coefficient is designed to encourage the swarm to prioritise the global search at the early stage while emphasising the local search at the later stage. PSO-MGLE is tested on the 2022 benchmark suite, scaled to 500, 1,000, and 2,000 dimensions. Experimental results demonstrate the competitive performance and good scalability of PSO-MGLE in comparison with seven state-of-the-art approaches.