基于高斯扰动的反向蜉蝣优化算法  

An opposition-based mayfly optimization algorithm based on Gaussian perturbation

作　　者：江佳玉 吴芸[1] 童林 吴雪颜 吴霄 JIANG jia-yu;WU Yun;TONG Lin;WU Xue-yan;WU Xiao(College of Science,Jiujiang University,Jiujiang 332005,Jiangxi,China)

机构地区：[1]九江学院理学院,江西九江332005

出　　处：《宝鸡文理学院学报（自然科学版）》2023年第1期19-26,共8页Journal of Baoji University of Arts and Sciences(Natural Science Edition)

基　　金：江西省自然科学基金项目(20224BAB201010);江西省教育厅科技项目(GJJ211823;GJJ211825);江西省2021年大学生创新创业训练计划项目(S202111843039);九江学院大学生创新创业训练计划项目(X202111843144)。

摘　　要：目的 解决蜉蝣优化算法收敛精度较低且易陷入局部最优解的不足。方法 将高斯扰动和混合反向学习策略与蜉蝣优化算法进行融合,提出一种基于高斯扰动的反向蜉蝣优化算法。该算法在雌雄蜉蝣种群中通过反向学习来扩大搜索空间,增加种群多样性;在迭代过程中对雄性蜉蝣的最优个体进行高斯扰动,防止算法陷入局部最优解。结果与结论将改进蜉蝣优化算法与其他7个对比算法在14个测试函数上进行数值实验,结果表明,改进蜉蝣优化算法具有更好的搜索能力和求解精度。Purposes—To solve the problem that the mayfly optimization algorithm(MA)has low convergence accuracy and is easy to fall into the local optimal solution.Methods—A Gaussian perturbation and a hybrid opposition-based learning strategy are mixed with the mayfly optimization algorithm to propose an opposition-based mayfly optimization algorithm based on Gaussian perturbation(GOMA).Opposition-based learning is performed on both male and female mayfly populations to expand search space and increase population diversity.Gaussian perturbation is introduced to the best individuals of male mayflies to avoid falling into local optimal solution during iteration.Result and Conclusion—The improved mayfly optimization algorithm(GOMA)is compared with 7 comparison algorithms on 14 test functions,the results show that the improved mayfly optimization algorithm is superior to other comparison algorithms in search ability and solution accuracy.

关 键 词：蜉蝣优化算法 高斯扰动 反向学习 全局寻优 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]