基于醉汉漫步和反向学习的灰狼优化算法  

A grey wolf optimization algorithm based on drunkard strolling and reverse learning

作　　者：刘炼 付绍昌[1] 黄辉先[1] LIU Lian;FU Shao-chang;HUANG Hui-xian(School of Automation and Electronic Information,Xiangtan University,Xiangtan 411105,China)

机构地区：[1]湘潭大学自动化与电子信息学院,湖南湘潭411105

出　　处：《计算机工程与科学》2021年第9期1558-1566,共9页Computer Engineering & Science

摘　　要：灰狼优化算法在优化后期易陷入局部最优,在求解高维函数时因其复杂度更高,陷入局部最优概率更大,针对上述问题提出基于醉汉漫步和反向学习的混合灰狼优化算法(DGWO)。在迭代过程中对每代种群中优势狼与最差狼进行反向学习并进行比较、重新排序后保留前3的狼,同时将采用醉汉漫步机制更新领导狼,参数A和C采用系数标量而不是GWO原始算法中的系数向量。通过10个标准测试函数(100维、500维和1000维)以及10维的CEC2013测试函数验证了算法的性能,并与PSO、GWO-CS和GWO算法进行了比较,结果表明,该混合灰狼优化算法在精度和收敛速度上都具有优势。此外,将改进的灰狼优化算法应用于两级运算放大器参数设计,以开环低频增益最大化为目标,验证该算法的实用性。The grey wolf optimization algorithm is easy to fall into the local optimum in the later stage of optimization.Because of its higher complexity when solving high-dimensional functions,the probability of falling into the local optimum is greater.To address this problem,this paper proposes a mixed grey wolf algorithm on the basis of both drunkard strolling and reverse learning,termed as DGWO.In the process of iteration,the dominant wolves are partially retained from the comparison between the dominant and the worst wolves via backward learning.Meanwhile,drunkard strolling is performed on the leader wolf,where the coefficient scalars are utilized in A and C instead of the coefficient vectors in the original algorithm.The effectiveness of the proposed method is investigated by 10 standard test functions(100D,500D and 1000D)as well as 10D CEC2013 test function,and compared with PSO,GWO-CS,and GWO algorithms.The simulation results demonstrate that the proposed DGWO algorithm performs better in terms of accuracy and convergence rate.In addition,the improved grey wolf algorithm is applied to the parameter design of the two-stage operational amplifier with the goal of maximizing the open-loop low-frequency gain to verify the practicability of our scheme.

关 键 词：高维复杂函数优化 灰狼优化 反向学习 醉汉漫步 CEC2013 运算放大器 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]