混合粒子群优化算法研究

Research on Hybrid Particle Swarm Optimization

提出将Hooke-Jeeves模式搜索方法嵌入粒子群优化算法中,以此构建混合粒子群优化算法.此外,在搜索过程中还加入变异操作来增加种群多样性,以避免早熟收敛.其中,局部搜索增加了算法的开发能力,而变异操作提高了算法的探测能力.探测与开发的折中则通过两个域值变量来完成.大量的测试函数研究表明,混合粒子群优化算法局部搜索能力有显著提高,且搜索到全局最优的概率更高.

A hybrid particle swarm optimization （HPSO） is proposed, where the Hooke-Jeeves pattern search is combined with PSO to speed up the local search, also mutation operation is embedded to avoid the common defect of premature convergence. Two thresholds are adopted to balance the exploration and exploitation abilities. The performance of new algorithm is demonstrated through extensive benchmark functions and compared with that of the PSO.The obtained results show that the local search ability is improved, and the probability of finding the global optimal value by HPSO is larger than that by using PSO.