混合柯西变异和均匀分布的蝗虫优化算法
作者:
作者单位:

1.贵州大学 a.大数据与信息工程学院;2.b.贵州省公共大数据重点实验室;3.贵州大学 大数据与信息工程学院

作者简介:

通讯作者:

中图分类号:

TP301

基金项目:

贵州省科技计划项目重大专项项目(黔科合重大专项字[2018] 3002,黔科合重大专项字[2016] 3022);贵州省公共大数据重点实验室开放课题(2017BDKFJJ004);贵州省教育厅青年科技人才成长项目(黔科合KY字[2016]124);贵州大学培育项目(黔科合平台人才[2017] 5788)


Hybrid Cauchy Mutation and Uniform Distribution of Grasshopper Optimization Algorithm
Author:
Affiliation:

1.a.College of Big Data and Information Engineering of GuizhouUniversity;2.b. Guizhou Provincial Key Laboratory of Public Big Data;3.College of Big Data and Information Engineering of GuizhouUniversity

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    由于位置更新公式存在的局部开发能力强而全局探索能力弱的缺陷,导致蝗虫优化算法(GOA)易陷入局部最优,易早熟收敛.因此提出混合柯西变异和均匀分布的蝗虫优化算法(HCUGOA),受柯西算子和粒子群算法的启发,提出具有分段思想的位置更新方式以增加种群多样性,增强全局探索能力;将柯西变异和反向学习的融合,对最优位置即目标值进行变异更新,提高算法跳出局部最优的能力;为了更好的平衡全局探索和局部开发,将均匀分布函数引入到非线性控制参数c,构建新的随机调整策略.通过对12个基准函数和CEC2014函数进行仿真实验以及Wilcoxon秩和检验的方法来评估改进算法的寻优能力,实验结果表明HCUGOA算法在收敛精度和收敛速度等方面得到了极大的改进.

    Abstract:

    Due to the strong local exploitation ability and the weak global exploration ability of the location update formula, the grasshopper optimization algorithm (GOA) was easy to fall into local optimum and easy to prematurely converge. Therefore, this paper proposed a hybrid Cauchy mutation and uniform distribution of grasshopper optimization algorithm (HCUGOA). Firstly, inspired by the cauchy operator and particle swarm optimization algorithm, a location update method with segmentation idea was proposed to increase the diversity of the population and to enhance the global exploration ability. Secondly, the fusion of cauchy mutation and opposition-based learning, the variation of the optimal position, which was, the target value, improved the ability of the algorithm to jump out of the local optimum; Finally, in order to better balance the global exploration and local exploitation, the uniform distribution function was introduced into the nonlinear control parameter c, so that could build a new random adjustment strategy. The optimization performance of the improved algorithm is evaluated by a sets of simulation experiments and Wilcoxon’s test on 12 benchmark functions and modern CEC 2014 functions. The experimental results show that the HCUGOA algorithm has been greatly improved in terms of convergence accuracy and convergence speed.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-11-18
  • 最后修改日期:2021-02-08
  • 录用日期:2020-03-18
  • 在线发布日期: 2020-03-30
  • 出版日期: