基于小波支持向量机特征分类的日径流组合预测——以宜昌三峡水库为例
|
摘要
河流径流预测作为水库调度和发电的重要前提,其预测精度直接影响水利工程的综合效益。基于径流历史数据,针对其波动和随机性提出一种小波分析-支持向量机(SVM)特征分类组合预测模型。该模型首先利用小波分解提取原始径流序列的高低频能量谱作为SVM样本标记,并对原始序列进行特征分类,分为"平稳型"和"突变型"序列,对应不同类型序列的小波近似信号和细节信号分别采用自回归和滑动平均模型(ARMA)和BP神经网络模型进行预测,再重构各序列预测结果。最后采用平均绝对百分比误差(MAPE)、均方根误差(RMSE)、希尔不等式系数(TIC)作为模型评价指标。结果表明:在3个评价指标下,所提模型都优于ARMA和BP神经网络模型,并具有更好预测稳定性。
As an important prerequisite for reservoir operation and power generation,the prediction accuracy of river runoff has a direct impact on the comprehensive benefits of water conservancy projects. Based on the historical data of runoff,this paper proposes a wavelet analysis support vector machine( SVM) feature classification combined forecasting model for its volatility and randomness. Firstly,the wavelet decomposition is used to extract the high and low frequency energy spectrum of the original runoff sequence as the SVM sample mark,and the original sequence is classified by feature,dividing into stationary and abrupt sequences,the wavelet approximation signals and the detail signals,corresponding to different types of sequences,are predicted by auto-regressive moving average model( ARMA) and BP neural network model respectively,then the prediction results of each sequence are reconstructed. Finally,the Mean Absolute Percentage Error( MAPE),the Root Mean Square Error( RMSE) and the Theil Inequality Coefficient( TIC) are used as the evaluation indexes of the model.The results show that: under the 3 evaluation indexes,the proposed model is better than the ARMA and BP neural network models,and it has better prediction stability.
As an important prerequisite for reservoir operation and power generation,the prediction accuracy of river runoff has a direct impact on the comprehensive benefits of water conservancy projects. Based on the historical data of runoff,this paper proposes a wavelet analysis support vector machine( SVM) feature classification combined forecasting model for its volatility and randomness. Firstly,the wavelet decomposition is used to extract the high and low frequency energy spectrum of the original runoff sequence as the SVM sample mark,and the original sequence is classified by feature,dividing into stationary and abrupt sequences,the wavelet approximation signals and the detail signals,corresponding to different types of sequences,are predicted by auto-regressive moving average model( ARMA) and BP neural network model respectively,then the prediction results of each sequence are reconstructed. Finally,the Mean Absolute Percentage Error( MAPE),the Root Mean Square Error( RMSE) and the Theil Inequality Coefficient( TIC) are used as the evaluation indexes of the model.The results show that: under the 3 evaluation indexes,the proposed model is better than the ARMA and BP neural network models,and it has better prediction stability.
引文
[1]Antonetti M,Scherrer S,Kienzler P M,et al.Process-based hydrological modelling:the potential of a bottom-up approach for runoff predictions in ungauged catchments[J].Hydrological Processes,2017,31:2 902-2 920.
[2]孟二浩,黄生志,黄强,等.融合大气环流异常因子的径流预报研究[J].水力发电学报,2017,36(8):34-42.
[3]于瑞宏,张宇瑾,张笑欣,等.无测站流域径流预测区域化方法研究进展[J].水利学报,2016,47(12):1 528-1 539.
[4]尹鑫卫,李晓玲,康燕霞,等.基于SCS-CN模型的沟垄微型集雨系统径流预测[J].生态学杂志,2015,34(12):3 502-3 508.
[5]刘国东,丁晶.BP网络用于水文预测的几个问题探讨[J].水利学报,1999,(1):65-70.
[6]Shoaib M,Shamseldin A Y,Melville B W,et al.A comparison between wavelet based static and dynamic neural network approaches for runoff prediction[J].Journal of Hydrology,2016,535:211-225.
[7]周娅,郭萍,古今今.基于BP神经网络的概率径流预测模型[J].水力发电学报,2014,33(2):45-50.
[8]Vapnik V N.The nature of statistical learning theory[M].New York:Springer,2000.
[9]叶碎高,彭勇,周惠成.基于PSO参数辨识SVM的中长期径流预测研究[J].大连理工大学学报,2011,51(1):115-120.
[10]Meng X,Yin M,Ning L,et al.A threshold artificial neural network model for improving runoff prediction in a karst watershed[J].Environmental Earth Sciences,2015,74(6):1-10.
[11]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.
[12]聂敏,刘志辉,刘洋,等.基于PCA和BP神经网络的径流预测[J].中国沙漠,2016,36(4):1 144-1 152.
[13]李娇,姜明媛,孙文超,等.基于BP神经网络的泉州市山美水库降雨径流模拟研究[J].北京师范大学学报(自然科学版),2013,49(2):170-174.
[14]黄巧玲,粟晓玲,杨家田.基于小波分解的日径流支持向量机回归预测模型[J].西北农林科技大学学报(自然科学版),2016,44(4):211-217.
[15]Patil S K,Valunjkar S S.Utility of coactive neuro-fuzzy inference system for runoff prediction in comparison with multilayer perception[J].International Journal of Engineering Research,2016,5(1):156-160.
[16]纪昌明,李荣波,张验科.等.基于小波分解的投影寻踪自回归组合模型及其在年径流预测中的应用[J].水力发电学报,2015,34(7):27-35.
[17]王秀杰,封桂敏,耿庆柱.小波分析组合模型在日径流预测中的应用研究[J].自然资源学报,2014,(5):885-893.
[18]Shi J,Liu Y,Yang Y,et al.Short-term wind power prediction based on wavelet transform-support vector machine and statistic characteristics analysis[C]∥Industrial and Commercial Power Systems Technical Conference,IEEE,2011:1 136-1 141.
[19]高阳,张碧玲,毛京丽,等.基于机器学习的自适应光伏超短期出力预测模型[J].电网技术,2015,39(2):307-311.
[20]Hartman E,Keeler J D,Kowalski J M.Layered neural networks with gaussian hidden units as universal approximations[J].Neural Computation,1990,2(2):210-215.
[21]王秀杰,练继建,费守明.基于小波消噪的混沌神经网络径流预报模型[J].水力发电学报,2008,27(5):37-40.
[22]易丹辉.数据分析与EViews应用[M].2版.北京:中国人民大学出版社,2014.
[23]谢中华.MATLAB统计分析与应用[M].北京:北京航空航天大学出版社,2010.
[2]孟二浩,黄生志,黄强,等.融合大气环流异常因子的径流预报研究[J].水力发电学报,2017,36(8):34-42.
[3]于瑞宏,张宇瑾,张笑欣,等.无测站流域径流预测区域化方法研究进展[J].水利学报,2016,47(12):1 528-1 539.
[4]尹鑫卫,李晓玲,康燕霞,等.基于SCS-CN模型的沟垄微型集雨系统径流预测[J].生态学杂志,2015,34(12):3 502-3 508.
[5]刘国东,丁晶.BP网络用于水文预测的几个问题探讨[J].水利学报,1999,(1):65-70.
[6]Shoaib M,Shamseldin A Y,Melville B W,et al.A comparison between wavelet based static and dynamic neural network approaches for runoff prediction[J].Journal of Hydrology,2016,535:211-225.
[7]周娅,郭萍,古今今.基于BP神经网络的概率径流预测模型[J].水力发电学报,2014,33(2):45-50.
[8]Vapnik V N.The nature of statistical learning theory[M].New York:Springer,2000.
[9]叶碎高,彭勇,周惠成.基于PSO参数辨识SVM的中长期径流预测研究[J].大连理工大学学报,2011,51(1):115-120.
[10]Meng X,Yin M,Ning L,et al.A threshold artificial neural network model for improving runoff prediction in a karst watershed[J].Environmental Earth Sciences,2015,74(6):1-10.
[11]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.
[12]聂敏,刘志辉,刘洋,等.基于PCA和BP神经网络的径流预测[J].中国沙漠,2016,36(4):1 144-1 152.
[13]李娇,姜明媛,孙文超,等.基于BP神经网络的泉州市山美水库降雨径流模拟研究[J].北京师范大学学报(自然科学版),2013,49(2):170-174.
[14]黄巧玲,粟晓玲,杨家田.基于小波分解的日径流支持向量机回归预测模型[J].西北农林科技大学学报(自然科学版),2016,44(4):211-217.
[15]Patil S K,Valunjkar S S.Utility of coactive neuro-fuzzy inference system for runoff prediction in comparison with multilayer perception[J].International Journal of Engineering Research,2016,5(1):156-160.
[16]纪昌明,李荣波,张验科.等.基于小波分解的投影寻踪自回归组合模型及其在年径流预测中的应用[J].水力发电学报,2015,34(7):27-35.
[17]王秀杰,封桂敏,耿庆柱.小波分析组合模型在日径流预测中的应用研究[J].自然资源学报,2014,(5):885-893.
[18]Shi J,Liu Y,Yang Y,et al.Short-term wind power prediction based on wavelet transform-support vector machine and statistic characteristics analysis[C]∥Industrial and Commercial Power Systems Technical Conference,IEEE,2011:1 136-1 141.
[19]高阳,张碧玲,毛京丽,等.基于机器学习的自适应光伏超短期出力预测模型[J].电网技术,2015,39(2):307-311.
[20]Hartman E,Keeler J D,Kowalski J M.Layered neural networks with gaussian hidden units as universal approximations[J].Neural Computation,1990,2(2):210-215.
[21]王秀杰,练继建,费守明.基于小波消噪的混沌神经网络径流预报模型[J].水力发电学报,2008,27(5):37-40.
[22]易丹辉.数据分析与EViews应用[M].2版.北京:中国人民大学出版社,2014.
[23]谢中华.MATLAB统计分析与应用[M].北京:北京航空航天大学出版社,2010.