Computer Engineering and Applications ›› 2020, Vol. 56 ›› Issue (7): 48-56.DOI: 10.3778/j.issn.1002-8331.1904-0203

Previous Articles     Next Articles

Reverse Learning Particle Swarm Optimization Based on Grey Wolf Optimization

ZHOU Rong, LI Jun, WANG Hao   

  1. 1.College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China
    2.Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan 430065, China
  • Online:2020-04-01 Published:2020-03-28

基于灰狼优化的反向学习粒子群算法

周蓉,李俊,王浩   

  1. 1.武汉科技大学 计算机科学与技术学院,武汉 430065
    2.智能信息处理与实时工业系统湖北省重点实验室,武汉 430065

Abstract:

To overcome the shortcomings of Particle Swarm Optimization(PSO) such as premature convergence, poor ability to escape from local optimum and low accuracy, a reverse learning PSO algorithm based on Grey Wolf Optimization(GWO) is proposed. Firstly, the inverse learning strategy is used to generate the inverse solution for the optimal particle, which enlarges the searching range of the population and enhances the global searching ability of the algorithm. Secondly, a new social learning method is used to improve the searching efficiency and mining performance of the non-optimal particle. At the same time, aiming at the problem of low convergence accuracy of PSO, the GWO algorithm is introduced and the convergence factor is disturbed to balance the global and local search performance of the algorithm and improve its accuracy. The simulation results on CEC_2017 test function show that under the same experimental conditions, the improved PSO algorithm has significantly improved the convergence accuracy and speed, and its performance is significantly better than the standard PSO algorithm.

Key words: Particle Swarm Optimization(PSO), inverse learning, Grey Wolf Optimization(GWO) algorithm, Beta distribution

摘要:

针对粒子群算法(PSO)易早熟收敛、逃离局部最优能力差、精度低等缺点,提出一种基于灰狼优化的反向学习粒子群算法。该算法对最优粒子采用反向学习策略产生反向解,扩大种群的搜索范围,增强了算法的全局搜索能力;对其非最优粒子采用新型社会学习方式,提高其搜索效率和开采性能;同时,针对PSO收敛精度较低的问题,引入灰狼优化算法,并对其收敛因子产生扰动,平衡算法全局和局部搜索性能并提高其精度。在CEC2017测试函数上进行仿真实验,结果表明,在相同的实验条件下,改进后的粒子群算法在收敛精度和收敛速度上有显著提升,且其性能明显优于标准粒子群算法。

关键词: 粒子群算法, 反向学习, 灰狼优化算法, 贝塔分布