解复杂多峰优化问题的双引导机制灰狼算法  

Grey wolf optimizer with dual guidance mechanism for complex multimodal problems

作　　者：孟团兴 覃华[1] MENG Tuan-xing;QIN Hua(School of Computer,Electronics and Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《计算机工程与设计》2023年第5期1378-1384,共7页Computer Engineering and Design

基　　金：国家自然科学基金项目(51667004、61762009)。

摘　　要：为解决复杂多峰优化问题高质量解难以获取的难题,分析灰狼算法解此类问题时易陷入局部最优的原因,提出一种解复杂多峰优化问题的双引导机制灰狼算法。对于当前适应度较好的个体,沿用传统灰狼算法引导机制探测个体,保留其局部搜索能力强的优点;对于适应度较差的个体,通过动态选择稀疏点算子或偏向差分变异算子的引导机制探索解空间新区域,增强灰狼算法跳出局部最优的能力。实例仿真计算结果表明,该算法所获计算精度优于相比较的其它算法。特别是Wilcoxon假设检验结果显示,其分别以96.67%、97.43%、93.15%的显著性优于传统灰狼算法、粒子群-灰狼混合算法及选择性反向灰狼算法。To solve the difficult problem of solving complex multimodal optimization problems with high quality,the reason that the grey wolf optimizer is easy to fall into local optimum was analyzed,and an improved grey wolf optimizer with dual guidance mechanism was proposed.For individuals with good fitness,the guidance mechanism of traditional grey wolf optimizer was used to search individuals’positions and retain its advantage of strong local search ability.For individuals with poor fitness,new regions of the solution space were explored by the guidance mechanism which dynamically selected sparse point operator or biased difference variation operator to enhance the ability of the grey wolf optimizer to jump out of local optimum.Simulation results show that the accuracy of the proposed algorithm is better than that of other algorithms.In particular,Wilcoxon hypothesis test results show that the proposed algorithm is better than the traditional grey wolf optimizer,hybrid algorithm of particle swarm optimization and grey wolf optimizer,and selective opposition based grey wolf optimization in terms of the significances of 96.67%,97.43%and 93.15%,respectively.

关 键 词：多峰优化问题 灰狼算法 双引导机制 稀疏度 稀疏点算子 偏向角 偏向差分变异算子 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]