基于莱维飞行和随机游动策略的灰狼算法

Grey Wolf Algorithm Based on Levy Flight and Random Walk Strategy

在标准灰狼优化算法寻优的中后期,由于衰减因子减小,灰狼群体中的个体均向领导层灰狼所在区域靠近,导致算法的全局寻优能力差,降低了寻优精度。针对该问题,提出了一种改进灰狼优化算法(Improved Grey Wolf Optimization,IGWO)。该算法首先分析了衰减因子对灰狼算法(Grey Wolf Optimization,GWO)的影响,提出了一种分段可调节衰减因子,用于平衡算法的勘探能力与开发能力。其可以根据不同优化问题来寻找适当的参数,实现更高精度的寻优,并且保证了在寻优过程的中后期,算法也具有一定的全局搜索能力。数值仿真实验表明,提高勘探比例有利于提高算法的收敛精度。同时,在寻优过程中,根据概率选择对领导层灰狼分别进行莱维飞行操作或随机游动操作。利用莱维飞行短距离搜索与偶尔较长距离行走相间的搜索特点,提高算法的全局寻优能力;利用随机游动相对集中的搜索特性,提高局部寻优能力。最后,对8个标准测试函数进行仿真实验,并与其他几种算法进行比较,实验结果表明,所提算法在寻优精度、算法稳定性及收敛速度上都有较大优势。

The individuals in the grey wolf group tend to approach to the area where the leadership grey wolf is located because of the reduction of attenuation factor in the middle and late stage of the optimization process for the standard grey wolf optimization algorithm,which results in poor global optimization ability and reduces the optimization accuracy of the algorithm.Aiming at this problem,an improved grey wolf optimization algorithm(IGWO)is proposed.Firstly,by analyzing the influence of the decay factor,an adjustable segmentation decay factor is presented to focus on proper balance between exploration ability and exploitation ability.The appropriate parameter is searched to achieve more precise optimization.And it ensures that the algorithm has a certain global search ability in the middle and later stages of the optimization process.The numerical simulation experiments show that increasing the exploration ratio is beneficial to improve the convergence accuracy of the algorithm.Meanwhile,leadership wolves are selected by probability to carry out levy flight operation or random walk operation respectively in the process of optimization.The global optimization ability of the algorithm is improved by the levy flight with the feature of short-range flight search and occasional long-distance walk.While the local optimization ability is improved by random walk with relatively centralized search range.Simulation experiments are conducted on optimization problems.The results show that compared with other algorithms,the improved algorithm has great performance in optimization precision,algorithm stability and convergence speed.