典型参数优化算法在新安江模型中的对比研究
DOI:
作者:
作者单位:

四川大学水利水电学院

作者简介:

通讯作者:

中图分类号:

P334+.92

基金项目:

四川省科技计划重点研发项目(2021YFS0285);科技部国家国际科技合作专项(2012DFG21780)


Comparative Study of Typical Parameter Optimization Algorithms in Xin"anjiang Model
Author:
Affiliation:

College of Water Resources and Hydropower,Sichuan University

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:

    为详细对比研究典型参数优化算法在新安江模型中的应用情况,选用4种典型优化算法:自适应遗传算法(AGA)、改进粒子群算法(IPSO)、SCE-UA和贝叶斯优化算法(BOA),以确定性系数为目标函数值,每种算法独立操作50次,每次迭代300次,在安徽省黄山市呈村流域对新安江模型参数进行率定,对比结果表明:AGA收敛值平均水平和集中程度较好,但收敛速度和稳定性较差;IPSO在所有算法中应用效果最好,但对参数初始值敏感,计算量大;SCE-UA稳定性和收敛速度较好,但收敛值平均水平和集中程度较差;BOA应用效果较差,但其计算量小,计算速度快。因此,应用IPSO优选新安江模型参数时,可以利用BOA优选结果作为IPSO初始参数值。应用AGA或SCE-UA率定新安江参数时,可以两者结合使用。

    Abstract:

    In order to compare and study the application of typical parameter optimization algorithms in Xin"anjiang model in detail, four typical optimization algorithms are selected: Adaptive Genetic Algorithm (AGA), Improved Particle Swarm Algorithm (IPSO), SCE-UA and Bayesian Optimization Algorithm ( BOA), the deterministic coefficient is the value of the objective function, each algorithm operates 50 times independently, and each iteration 300 times. The parameters of the Xin"anjiang model are calibrated in the Chengcun watershed of Huangshan City, Anhui Province. The comparison results show that: AGA convergence value The average level and concentration are better, but the convergence speed and stability are poor; IPSO has the best application effect in all algorithms, but it is sensitive to the initial values of parameters and has a large amount of calculation; SCE-UA has better stability and convergence speed, but The average level of convergence and the degree of concentration are poor; the BOA application effect is poor, but its calculation is small and the calculation speed is fast. Therefore, when applying IPSO to optimize the parameters of the Xin"anjiang model, the BOA optimization results can be used as the initial parameter values of IPSO. When applying AGA or SCE-UA to calibrate Xin"anjiang parameters, both can be used in combination.

    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:2021-10-30
  • 最后修改日期:2021-10-30
  • 录用日期:2022-04-27
  • 在线发布日期:
  • 出版日期: