非线性自适应分组灰狼算法  

Nonlinear Adaptive Grouping Grey Wolf Optimization Algorithm

作　　者：马威 王巍[1] 曹颖 MA Wei;WANG Wei;CAO Ying(College of Engineering and Technology,Northeast Forestry University,Harbin Heilongjiang 150040,China)

机构地区：[1]东北林业大学工程技术学院,黑龙江哈尔滨150040

出　　处：《计算机仿真》2024年第6期441-447,587,共8页Computer Simulation

基　　金：中央高校基本科研业务费专项资助基金(2572019BL04);黑龙江省留学归国人员科学基金项目(LC201407)。

摘　　要：针对灰狼算法(grey wolf optimization, GWO)收敛速度慢、易陷入局部最优的问题,提出了一种非线性自适应分组灰狼算法(Nonlinear Adaptive Grouping Grey Wolf Optimization, NAGGWO)。首先,提出CPM映射生成初始种群,提高种群多样性;随后,提出一种“S”型非线性控制参数用来平衡算法的开采与探索能力;最后,采用自适应分组策略将狼群分为捕食组、游荡组和搜索组,对不同组灰狼个体分别采用改进的差分进化策略、随机反向学习策略以及算数优化算法(Arithmetic Optimization Algorithm, AOA)中的乘除算子进行位置更新,以改善GWO的收敛速度及精度。通过选取12个测试函数对NAGGWO进行仿真,结果表明在相同条件下,NAGGWO在求解低维问题和高维问题中相比其它算法都具有显著优势。To solve the problems of slow convergence and easy falling into the local optimum of the gray wolf opti⁃mization algorithm,the nonlinear adaptive grouping grey wolf optimization is proposed.First,CPM mapping is used to generate the initial population to improve the population diversity.Subsequently,an‘S’type nonlinear control param⁃eter is proposed to balance the exploitation and exploration ability of the algorithm.Finally,an adaptive grouping strat⁃egy is used to divide the wolf population into predators,wanderers and searchers.The improved differential evolution strategy,the stochastic reverse learning strategy and the multiplication and division operators in AOA are used to up⁃date the position of different groups of gray wolf individuals to improve the convergence speed and accuracy of GWO.The 12 test functions were selected to test the performance of NAGGWO for simulation experiments.The results show that under the same conditions,NAGGWO has significant advantages over other algorithms in solving both low-dimen⁃sional and high-dimensional problems.

关 键 词：灰狼优化算法 自适应分组 算数优化算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]