基于集合经验模式分解的ARIMA行业售电量预测模型
|
摘要
售电量的准确预测是电力市场课题研究的重要内容之一,目前已有许多模型用于售电量预测。在此背景下,考虑售电量时间序列的非线性、波动性和周期性,提出基于集合经验模式分解和自回归积分滑动算法的预测模型。该模型首先对售电量时间序列进行集合经验模态分解,通过添加白噪声得到不同时间尺度分布的售电量时间序列,分解后得到一系列相对平稳的本征模态函数和趋势项,然后利用自回归积分滑动算法对各平稳化本征模态函数和趋势项分别进行预测,得到各分量的预测结果,最后将分量预测结果叠加得到最终的售电量预测值。基于历史统计售电量数据的预测结果分析表明,基于集合经验模式分解的ARIMA模型具有良好的预测精度。
The accurate prediction of electricity sales is an essential part of electricity market resrearch. This paper presents an ARIMA model based on the ensemble empirical mode decomposition in consideration of the nonlinearity, volatility and periodicity of electricity sales. Firstly, the ensemble empirical mode decomposition is utilized to decompose the time series of electricity sales with different time scales by adding white noise. After decomposition, a series of relatively stable intrinsic mode functions and trend items are obtained. Then, the ARIMA model is utilized to predict the steady-state intrinsic mode functions and trend items respectively in order to get the prediction results of each component. Finally, the result of component forecasting is added together to get the final forecast of electricity sales. The analysis of prediction results based on the historical sales data shows that ARIMA model based on set empirical mode decomposition has good prediction accuracy.
The accurate prediction of electricity sales is an essential part of electricity market resrearch. This paper presents an ARIMA model based on the ensemble empirical mode decomposition in consideration of the nonlinearity, volatility and periodicity of electricity sales. Firstly, the ensemble empirical mode decomposition is utilized to decompose the time series of electricity sales with different time scales by adding white noise. After decomposition, a series of relatively stable intrinsic mode functions and trend items are obtained. Then, the ARIMA model is utilized to predict the steady-state intrinsic mode functions and trend items respectively in order to get the prediction results of each component. Finally, the result of component forecasting is added together to get the final forecast of electricity sales. The analysis of prediction results based on the historical sales data shows that ARIMA model based on set empirical mode decomposition has good prediction accuracy.
引文
[1]陈毅波,郑玲,姚建刚.基于粗糙集理论与D-S证据理论改进的多元回归负荷预测方法研究[J].电力系统保护与控制,2016,44(6):62-67.CHEN Yi-bo,ZHENG Ling,YAO Jian-gang.Improved multiple regression load forecasting method based on rough set theory and D-S evidence theory[J].Power System Protection and Control,2016,44(6):62-67.
[2]何耀耀,许启发,杨善林,等.基于RBF神经网络分位数回归的电力负荷概率密度预测方法[J].中国电机工程学报,2013,33(1):93-98.HE Yao-yao,XU Qi-fa,YANG Shan-lin,et al.A power load probability density forecasting method based on RBF neural ne-twork quantile regression[J].Proceedings of the CSEE,2013,33(1):93-98.
[3]颜伟,程超,薛斌,等.结合X12乘法模型和ARIMA模型的月售电量预测方法[J].电力系统及其自动化学报,2016,28(5):74-80.YAN Wei,CHENG Chao,XUE Bin,et al.Forecasting for monthly electricity consumption using X12 multiplication method and ARIMA model[J].Proceedings of the CSU-EPSA,2016,28(5):74-80.
[4]麦鸿坤,肖坚红,吴熙辰,等.基于R语言的负荷预测ARIMA 模型并行化研究[J].电网技术,2015,39(11):3 216-3 220.MAI Hong-kun,XIAO Jian-hong,WU Xi-chen,et al.Researchon ARIMA model parallelization in load prediction based onR language[J].Power System Technology,2015,39(11):3 216-3 220.
[5]王贺,胡志坚,陈珍,等.基于集合经验模态分解和小波神经网络的短期风功率组合预测[J].电工技术学报,2013,28(9):137-144.WANG He,HU Zhi-jian,CHEN Zhen,et al.A hybrid model for wind power forecasting based on ensemble empirical mode decomposition and wavelet neural networks[J].Transactions of China Electrotechnical Society,2013,28(9):137-144.
[6]田中大,李树江,王艳红,等.基于小波变换的风电场短期风速组合预测[J].电工技术学报,2015,30(9):112-120.TIAN Zhong-da,LI Shu-jiang,WANG Yan-hong,et al.Short-term wind speed combined prediction for wind farms basedon wavelet transform[J].Transactions of China Electrotechnical Society,2015,30(9):112-120.
[7]肖迁,李文华,李志刚,等.基于改进的小波-BP神经网络的风速和风电功率预测[J].电力系统保护与控制,2014,42(15):80-86.XIAO Qian,LI Wen-hua,LI Zhi-gang et al.Wind speed and power prediction based on improved wavelet-BP neural network[J].Power System Protection and Control,2014,42(15):80-86.
[8]叶林,刘鹏.基于经验模态分解和支持向量机的短期风电功率组合预测模型[J].中国电机工程学报,2011,31(31):102-108.YE Lin,LIU Peng.Combined model based on EMD-SVM forshort-term wind power prediction[J].Proceedings of the CSEE,2011,31(31):102-108.
[9]茆美琴,龚文剑,张榴晨,等.基于EEMD-SVM方法的光伏电站短期出力预测[J].中国电机工程学报,2013,33(34):17-24.MAO Mei-qin,GONG Wen-jian,ZHANG Liu-chen,et al.Short-term photovoltaic generation forecasting based on EEMD-SVM combined method[J].Proceedings of the CSEE,2013,33(34):17-24.
[10]郑近德,程军圣,杨宇.改进的EEMD算法及其应用研究[J].振动与冲击,2013,32(21):21-26,46.ZHENG Jin-de,CHENG Jun-sheng,YANG Yu.Modified EEM-D algorithm and its applications[J].Journal of Vibration and Shock,2013,32(21):21-26,46.
[11]安怀志.希尔伯特黄变换理论和应用的研究[D].哈尔滨:哈尔滨工程大学,2008.
[12]Wang L Y,Wang Q,Wang X L,et al.An improved extension method of EMD based on SVRM[J].Applied Mechanics and Materials,2014,(543-547):2 697-2 701.
[13]黄诚惕.希尔伯特—黄变换及其应用研究[D].成都:西南交通大学,2006.
[14]Zhang meijun,Han Sichen,Wang Chuang,et al.Improved EEMD method research[J].Advanced Materials Research,2012,(479-481):1 180-1 185.
[15]Contreras J,Espinola R,Nogales F J,et al.ARIMA models to predict next-day electricity prices[J].IEEE Transactions on Power Systems,2003,18(3):1 014-1 020.
[16]Conejo A J,Plazas M A,Espinola R,et al.Day-ahead electricity price forecasting using the wavelet transform and ARIMA models[J].IEEE Transactions on Power Systems,2005,20(2):1 035-1 042.
[17]Sowell F.Modeling long-run behavior with the fractional ARIMA model[J].Journal of Monetary Economics,1992,29(2):277-302.
[2]何耀耀,许启发,杨善林,等.基于RBF神经网络分位数回归的电力负荷概率密度预测方法[J].中国电机工程学报,2013,33(1):93-98.HE Yao-yao,XU Qi-fa,YANG Shan-lin,et al.A power load probability density forecasting method based on RBF neural ne-twork quantile regression[J].Proceedings of the CSEE,2013,33(1):93-98.
[3]颜伟,程超,薛斌,等.结合X12乘法模型和ARIMA模型的月售电量预测方法[J].电力系统及其自动化学报,2016,28(5):74-80.YAN Wei,CHENG Chao,XUE Bin,et al.Forecasting for monthly electricity consumption using X12 multiplication method and ARIMA model[J].Proceedings of the CSU-EPSA,2016,28(5):74-80.
[4]麦鸿坤,肖坚红,吴熙辰,等.基于R语言的负荷预测ARIMA 模型并行化研究[J].电网技术,2015,39(11):3 216-3 220.MAI Hong-kun,XIAO Jian-hong,WU Xi-chen,et al.Researchon ARIMA model parallelization in load prediction based onR language[J].Power System Technology,2015,39(11):3 216-3 220.
[5]王贺,胡志坚,陈珍,等.基于集合经验模态分解和小波神经网络的短期风功率组合预测[J].电工技术学报,2013,28(9):137-144.WANG He,HU Zhi-jian,CHEN Zhen,et al.A hybrid model for wind power forecasting based on ensemble empirical mode decomposition and wavelet neural networks[J].Transactions of China Electrotechnical Society,2013,28(9):137-144.
[6]田中大,李树江,王艳红,等.基于小波变换的风电场短期风速组合预测[J].电工技术学报,2015,30(9):112-120.TIAN Zhong-da,LI Shu-jiang,WANG Yan-hong,et al.Short-term wind speed combined prediction for wind farms basedon wavelet transform[J].Transactions of China Electrotechnical Society,2015,30(9):112-120.
[7]肖迁,李文华,李志刚,等.基于改进的小波-BP神经网络的风速和风电功率预测[J].电力系统保护与控制,2014,42(15):80-86.XIAO Qian,LI Wen-hua,LI Zhi-gang et al.Wind speed and power prediction based on improved wavelet-BP neural network[J].Power System Protection and Control,2014,42(15):80-86.
[8]叶林,刘鹏.基于经验模态分解和支持向量机的短期风电功率组合预测模型[J].中国电机工程学报,2011,31(31):102-108.YE Lin,LIU Peng.Combined model based on EMD-SVM forshort-term wind power prediction[J].Proceedings of the CSEE,2011,31(31):102-108.
[9]茆美琴,龚文剑,张榴晨,等.基于EEMD-SVM方法的光伏电站短期出力预测[J].中国电机工程学报,2013,33(34):17-24.MAO Mei-qin,GONG Wen-jian,ZHANG Liu-chen,et al.Short-term photovoltaic generation forecasting based on EEMD-SVM combined method[J].Proceedings of the CSEE,2013,33(34):17-24.
[10]郑近德,程军圣,杨宇.改进的EEMD算法及其应用研究[J].振动与冲击,2013,32(21):21-26,46.ZHENG Jin-de,CHENG Jun-sheng,YANG Yu.Modified EEM-D algorithm and its applications[J].Journal of Vibration and Shock,2013,32(21):21-26,46.
[11]安怀志.希尔伯特黄变换理论和应用的研究[D].哈尔滨:哈尔滨工程大学,2008.
[12]Wang L Y,Wang Q,Wang X L,et al.An improved extension method of EMD based on SVRM[J].Applied Mechanics and Materials,2014,(543-547):2 697-2 701.
[13]黄诚惕.希尔伯特—黄变换及其应用研究[D].成都:西南交通大学,2006.
[14]Zhang meijun,Han Sichen,Wang Chuang,et al.Improved EEMD method research[J].Advanced Materials Research,2012,(479-481):1 180-1 185.
[15]Contreras J,Espinola R,Nogales F J,et al.ARIMA models to predict next-day electricity prices[J].IEEE Transactions on Power Systems,2003,18(3):1 014-1 020.
[16]Conejo A J,Plazas M A,Espinola R,et al.Day-ahead electricity price forecasting using the wavelet transform and ARIMA models[J].IEEE Transactions on Power Systems,2005,20(2):1 035-1 042.
[17]Sowell F.Modeling long-run behavior with the fractional ARIMA model[J].Journal of Monetary Economics,1992,29(2):277-302.