基于BA-LSSVM模型的月径流预测方法

中国农村水利水电 ›› 2017 ›› (3) : 9-12.

水文水资源

武群丽,彭晨阳

作者信息 +

The Application of Bat Algorithm and Least Squares Support Machine to Monthly Runoff Forecasting

WU Qun-li,PENG Chen-yang

Author information +

稿件信息 +

摘要

针对最小二乘支持向量机模型传统参数选择方法费时且效果差的问题，本文利用蝙蝠算法的模型简单、快速收敛和全局搜索能力强的特点，优化模型的正则化参数和核函数参数，对水文时间序列建立最小二乘支持向量机预测模型。基于某水文站2000-2014年月径流资料对模型进行训练和预测，并与使用粒子群算法优化参数确定的最小二乘支持向量机模型，网格搜索及交叉验证优选参数确定的最小二乘支持向量机模型及BP神经网络模型进行比较。计算结果表明，基于蝙蝠算法优化最小二乘支持向量机模型具有很好的适用性和较高的预测精度，为利用最小二乘支持向量机模型解决非线性的水文时间序列问题提供了新的方向。

Abstract

Regarding the inefficiency and poor effect of traditional parameter selection methods in least squares support machines,the bat algorithm equipped with modeling simplification,powerful searching ability and fast convergence is employed to optimize the regularization parameter and kernel function parameter,and the least squares support vector machine prediction model for hydrological time series is proposed. In the light of the monthly runoff data of Liu Zhou Hydrological Station from 2000 to 2014,the least squares support machine model with the pertinent parameters being optimized by particle swarm optimization algorithm,the least squares support machine model with the relevant parameters being determined by using grid search and cross validation method,and back propagation neutral network model are utilized for comparison. The simulation results indicate that the least squares support machine model based on bat algorithm has better applicability and higher prediction accuracy,which offers a new approach for solving the problems of the nonlinear hydrological time series.

导出引用

武群丽彭晨阳. 基于BA-LSSVM模型的月径流预测方法[J].中国农村水利水电, 2017(3): 9-12

WU Qun-li, PENG Chen-yang. The Application of Bat Algorithm and Least Squares Support Machine to Monthly Runoff Forecasting[J].China Rural Water and Hydropower, 2017(3): 9-12

参考文献

参考文献：
[1] 张楠,夏自强,江红. 基于多因子量化指标的支持向量机径流预测[J]. 水利学报, 2010, 41(11): 1318-1324.
[2] 杨旭,栾继虹,冯国章. 中长期水文预报研究评述与展望[J]. 西北农业大学学报, 2000, 28(6): 203-207.
[3] Govindaraju RS. Artificial Neural Networks in Hydrology. I: Preliminary Concepts[J]. Journal of Hydrologic Engineering, 2000, 5(2): 115-123.
[4] Govindaraju RS. Artificial Neural Networks in Hydrology. II: Hydrologic Applications[J]. Journal of Hydrologic Engineering, 2000, 5(2): 124-137.
[5] 廖杰,王文圣,李跃清,等. 支持向量机及其在径流预测中的应用[J]. 四川大学学报(工程科学版), 2006, 38(6): 24-28.
[6] 张兰影,庞博,徐宗学,等. 基于支持向量机的石羊河流域径流模拟适用性评价[J]. 干旱区资源与环境, 2013, 27(7): 113-118.
[7] 卫太祥,马光文,黄炜斌. 基于惩罚加权支持向量机回归的径流预测模型[J]. 水力发电学报, 2012, 31(6): 35-38, 43.
[8] Yoon H, Jun S, Hyun Y, et al. A Comparative Study of Artificial Neural Networks and Support Vector Machines for Predicting Groundwater Levels in a Coastal Aquifer[J]. Journal of Hydrology, 2011, 396(1): 128-138.
[9] 唐奇,王红瑞,许新宜,等. 基于混合核函数SVM水文时序模型及其应用[J]. 系统工程理论与实践, 2014, 34(2): 521-529.
[10] 黄巧玲,粟晓玲. 基于小波支持向量机耦合的月径流预测方法[J]. 水力发电学报, 2015, 34(3): 1-7.
[11] Suykens J, Vandewalle J. Least Squares Support Vector Machine Classifiers[J]. Neural processing letters, 1999, 9(3): 293-300.
[12] 陶凤玲,武晟,余生才,等. 基于最小二乘支持向量机的龙羊峡径流预测[J]. 水文, 2008, 28(4): 23, 29-30.
[13] 李佳,马光文,杨忠伟,等. 基于粒子群最小二乘支持向量机的径流预测[J]. 人民长江, 2012, 43(S2): 60-62.
[14] 李彦彬,尤凤,黄强,等. 多元变量径流预测的最小二乘支持向量机模型[J]. 水力发电学报, 2010, 29(3): 28-33.
[15] 崔庆,马孝义,陈海涛. 最小二乘支持向量机模型在径流预报中的应用[J]. 中国农村水利水电, 2012, (12): 63-65.
[16] 周秀平,李天翔,王文圣. 年径流预测的最小二乘支持向量机-马尔可夫链组合模型[J]. 水力发电学报, 2013, 32(4): 16-19.
[17] 李文莉,李郁侠. 基于粒子群最小二乘支持向量机的水文预测[J]. 计算机应用, 2012, 32(4): 1188-1190.
[18] 代兴兰. 遗传算法与最小二乘支持向量机在年径流预测中的应用[J]. 水资源与水工程学报, 2014, 25(6): 231-235.
[19] Yang X. Nature Inspired Cooperative Strategies for Optimization (NICSO 2010)[M]. [Sl.]: Springer, 2010: 65-74.
[20] Hafezi R, Shahrabi J, Hadavandi E. A Bat-neural Network Multi-agent System (BNNMAS) for Stock Price Prediction: Case Study of DAX Stock Price[J]. Applied Soft Computing, 2015, 29: 196-210.
[21] Meng X,Gao X,Liu Y, et al. A Novel Bat Algorithm with Habitat Selection and Doppler Effect in Echoes for Optimization[J]. Expert Systems with Applications, 2015, 42(17): 6350-6364.
[22] Senthilkumar P, Vanitha NS. A Unified Approach to Detect the Record Duplication Using Bat Algorithm and Fuzzy Classifier for Health Informatics[J]. Journal of Medical Imaging and Health Informatics, 2015, 5(6): 1121-1132.
[23] Rao BV,Kumar GN. Optimal Power Flow By Bat Search Algorithm for Generation Reallocation with Unified Power Flow Controller[J]. International Journal of Electrical Power & Energy Systems, 2015, 68: 81-88.
[24] Yang N, Le M. Optimal Design of Passive Power Filters Based on Multi-objective Bat Algorithm and Pareto Front[J]. Applied Soft Computing, 2015, 35: 257-266.
[25] GB/T22482-2008. 水文情报预报规范[S]. 北京:中国水利水电出版社,2008.

PDF(869 KB)

访问

引用

详细情况

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献

收稿日期	修订日期	出版日期
2016-06-02	2016-07-18	2017-03-15
发布日期
2020-04-25

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献