• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Water Resources Management >A Novel Multi-Objective Shuffled Complex Differential Evolution Algorithm with Application to Hydrological Model Parameter Optimization
【24h】

A Novel Multi-Objective Shuffled Complex Differential Evolution Algorithm with Application to Hydrological Model Parameter Optimization

机译：一种新的多目标混洗复杂差分进化算法及其在水文模型参数优化中的应用

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Practice experience suggests that the traditional calibration of hydrological models with single objective cannot properly measure all of the behaviors of the hydrological system. To circumvent this problem, in recent years, a lot of studies have looked into calibration of hydrological models with multi-objective. In this paper, we propose a novel multi-objective evolution algorithm entitled multi-objective shuffled complex differential evolution (MOSCDE) algorithm, which is an extension of the famous single objective algorithm, shuffled complex evolution (SCE-UA) algorithm, to the multi-objective framework. This new proposed algorithm replaces the simplex search used in SCE-UA with the differential evolution (DE) algorithm and can more thoroughly utilize the information of the individuals in the evolutionary population and improve the search ability of the algorithm. Meanwhile, the Cauchy mutation (CM) operator is employed to prevent the algorithm from falling into the local optimal region of the feasible space. Moreover, two types of archive sets are employed to further improve the performance of the algorithm. The efficacy of the MOSCDE algorithm is first tested on five benchmark problems. After achieving satisfactory performance on the test problems, the MOSCDE is applied to multi-objective parameter optimization of a hydrological model for daily runoff forecasting. The results show that the MOSCDE algorithm can be a viable alternative for multi-objective parameter optimization of hydrological model.
机译：实践经验表明，传统的单目标水文模型标定不能正确地测量水文系统的所有行为。为了解决这个问题，近年来，许多研究都在对具有多目标的水文模型进行校准。在本文中，我们提出了一种新颖的多目标进化算法，称为多目标改组复杂差分演化（MOSCDE）算法，它是著名的单目标算法，改组复杂演化（SCE-UA）算法的扩展。目标框架。该新提出的算法用差分进化（DE）算法代替了SCE-UA中使用的单纯形搜索，可以更充分地利用进化种群中个体的信息，并提高算法的搜索能力。同时，采用柯西突变（CM）算子来防止算法落入可行空间的局部最优区域。此外，采用了两种类型的存档集来进一步提高算法的性能。首先在五个基准问题上测试了MOSCDE算法的有效性。在测试问题上取得令人满意的性能后，MOSCDE被应用于水文模型的多目标参数优化，以进行每日径流预报。结果表明，MOSCDE算法可以作为水文模型多目标参数优化的可行选择。

著录项

  • 来源
    《Water Resources Management》 |2013年第8期|29232924-2946|共24页
  • 作者

    Jun Guo; Jianzhong Zhou; Qiang Zou; Yi Liu; Lixiang Song;

  • 作者单位

    School of Hydropowcr and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, China,Hubci Key Laboratory of Digital Valley Science and Technology, Wuhan 430074, China,Hunan Electric Power Test & Research Institute, Changsha 410007, China;

    School of Hydropowcr and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, China,Hubci Key Laboratory of Digital Valley Science and Technology, Wuhan 430074, China;

    School of Hydropowcr and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, China,Hubci Key Laboratory of Digital Valley Science and Technology, Wuhan 430074, China;

    School of Hydropowcr and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, China,Hubci Key Laboratory of Digital Valley Science and Technology, Wuhan 430074, China;

    Laboratory of Numerical Modeling Technique for Water Resources, Department of Water Resources and Environment, Pearl River Water Resources Research Institute, Guangzhou 510623, China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    multi-objective optimization; differential evolution; hydrological model; model calibration; parameter optimization; runoff forecasting;

    机译：多目标优化;差异进化水文模型模型校准;参数优化;径流预报;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号