基于CEEMD和随机森林算法的短期风电功率预测
|
摘要
提出一种基于完备总体经验模态分解(CEEMD)和随机森林(RF)算法的短期风电功率预测模型。首先,采用CEEMD算法将风电功率原始序列分解为若干特征互异的模态函数,计算各模态函数样本熵并将样本熵值相近的模态函数合并为新的分量。同时,采用偏自相关函数对不同分量确定输入变量集合,避免了人工经验选取的不足。然后,对每一分量建立随机森林预测模型,将各分量预测结果叠加获得短期风电功率预测值。最后,通过算例验证了所提模型的有效性。
Accurate wind power forecasting is of great significance to ensure the power grid safe and stable operation.However,short-term wind power forecasting is difficult to obtain high prediction accuracy due to the strong volatility and randomness.A short-term wind power prediction model is proposed based on complete ensemble empirical mode decomposition(CEEMD)and random forest(RF)algorithm.Firstly,the original wind power sequence is decomposed into several mode functions by CEEM D.At the same time,the sample entropy for each mode function is calculated and the new component with similar sample entropy value is reconstructed.The partial autocorrelation function is applied to select input variables and avoids deficiency of artificial experience selection.Then,the random forest forecasting model is established for each new component,and the wind power prediction values can be obtained by summing up the forecasting results of different components.Finally,the simulation case verifies the effectiveness of proposed model.
Accurate wind power forecasting is of great significance to ensure the power grid safe and stable operation.However,short-term wind power forecasting is difficult to obtain high prediction accuracy due to the strong volatility and randomness.A short-term wind power prediction model is proposed based on complete ensemble empirical mode decomposition(CEEMD)and random forest(RF)algorithm.Firstly,the original wind power sequence is decomposed into several mode functions by CEEM D.At the same time,the sample entropy for each mode function is calculated and the new component with similar sample entropy value is reconstructed.The partial autocorrelation function is applied to select input variables and avoids deficiency of artificial experience selection.Then,the random forest forecasting model is established for each new component,and the wind power prediction values can be obtained by summing up the forecasting results of different components.Finally,the simulation case verifies the effectiveness of proposed model.
引文
[1]JUNG J,BROADWATER R P.Current status and future advances for wind speed and power forecasting[J].Renewable&Sustainable Energy Reviews,2014,31(2):762-777.
[2]黄晗,孙堃,刘达.基于随机森林的电力系统小时负荷预测研究[J].智慧电力,2018,46(5):8-14.HU ANG Han,SUN Kun,LIU Da.Hourly load forecasting of power system based on random forest[J].Smart Power,2018,46(5):8-14.
[3]PEDRO GOMES,RUI CASTRO.Wind speed and wind power forecasting using statistical models:autoregressive moving average and artificial neural networks[J].International Journal of Sustainable Energy Development,2012,1(2):41-50.
[4]CASSOLA F,BURLANDO M.Wind speed and wind energy forecast through Kalman filtering of numerical weather prediction model output[J].Applied Energy,2012,99(6):154-166.
[5]喻圣,邹红波,余凡,等.模糊神经网络在电力系统短期负荷预测中的应用[J].智慧电力,2018,46(11):88-91.YU Shen,ZOU Hongbo, YU Fan,et al.Application of fuzzy neural network in power short-term load forecasting[J].Smart Power,2018,46(1 1):88-91.
[6]李若晨,朱帆,朱永利,等.基于改进乌鸦算法和ESN神经网络的短期风电功率预测[J].电力系统保护与控制,2018,46(17):83-88.LI Ruochen,ZHU Fan,ZHU Yongli,et al.Short-term power load forecasting using recurrent neural network with restricted Boltzmann machine[J].Power System Protection and Control,2018,46(17):83-88.
[7]YAN J,LIU Y,HAN S,et al.Wind power grouping forecasts and its uncertainty analysis using optimized relevance vector machine[J].Renewable&Sustainable Energy Review,2013,27(6):613-621.
[8]张雨金,杨凌帆,葛双冶,等.基于Kmeans-SVM的短期光伏发电功率预测[J].电力系统保护与控制,2018,46(21):118-124.ZHANG Yujin,YANG Lingfan,GE Shuangye,et al.Shortterm photovoltaic power forecasting based on Kmeans algorithm and support vector machine[J].Power System Protection and Control,2018,46(21):1 18-124.
[9]王贺,胡志坚,张翌晖,等.基于IPSO-LSSVM的风电功率短期预测研究[J].电力系统保护与控制,2012,40(24):107-112.WANG He,HU Zhijian,ZHANG Yihui,et al.Shortterm prediction of wind power based on IPSO-LSSVM[J].Power System Protection and Control,2012,40(24):107-112.
[10]陶玉波,陈昊,秦晓辉,等.短期风电功率预测概念和模型与方法[J].电力工程技术,2018,37(5):7-13.TAO Yubo,CHEN Hao,QIN Xiaohui,et al.A review of the short-term wind power forecasting theory,model and approach[J].Jiangsu Electrical Engineering,2018,37(5):7-13.
[11]张亚超,刘开培,秦亮.基于VMD-SE和机器学习算法的短期风电功率多层级综合预测模型[J].电网技术,2016,40(5):1334-1340.ZHANG Yachao,LIU Kaipei,QIN Liang.Short-term wind power multi-leveled combined forecasting model based on variational mode decomposition-sample entropy and machine learning algorithms[J].Power System Technology,2016,40(5):1334-1340.
[12]ZHANG W,LIU F,ZHENG X,et al.A hybrid EMDSVM based short-term wind power forecasting model[C].Brisbane:Power and Energy Engineering Conference,IEEE,2016:1-5.
[13]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 Zhijian,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.
[14]TORRES M E,COLO MINAS M A,SCHLOTTHAUER G,et al.A comp lete ense mble empirical mode decomposition with adaptive noise[C].Acoustics:IEEE International Conference:Speech and Signal Processing,2011:4144-4147.
[15]BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[16]李青,李军,马昊.基于互补型集成经验模态分解-模糊熵和回声状态网络的短期电力负荷预测[J].计算机应用,2014,34(12):3651-3655.LI Qing,LI Jun,MA Hao.Short-term electricity load forecasting based on complementary ensemble empirical mode decomposition-fuzzy permutation and echo state network[J].Journal of Computer Applications,2014,34(12):3651-3655.
[17]潘云,张晓星,张英,等.基于互补集合经验模态分解法的变压器局部放电信号去噪方法[J].广东电力,2017,30(10):7-13.PAN Yun,ZHANG Xiaoxing,ZHANG Ying,et al.Denoising method for transformer partial discharge signals based on complete ensemble empirical mode decomposition[J].Guangdong Electric Power,2017,30(10):7-13.
[18]周涛涛,朱显明,彭伟才,等.基于CEEMD和排列熵的故障数据小波阈值降噪方法[J].振动与冲击,2015,34(23):207-211.ZHOU Taotao,ZHU Xianming,PENG Weicai,et al.A wavelet threshold denoising method for fault data based on CEEMD and permutation entropy[J].Journal of Vibration and Shock,2015,34(23):207-211.
[19]GRZEGORZ DUDEK.Short-term load forecasting using random forests[C].Warsaw:Proceedings of the 7th IEEE International Conference Intelligent Systems IS 2014,821-828.
[20]梁智,孙国强,卫志农,等.基于变量选择与高斯过程回归的短期负荷预测[J].电力建设,2017,38(2):122-128.LIANG Zhi,SUN Guoqiang,WEI Zhinong,et al.Shortterm load forecasting based on variable selection and gaussian process regression[J].Electric Power Construction,2017,38(2):122-128.
[21]张学清,梁军,张熙,等.基于样本熵和极端学习机的超短期风电功率组合预测模型[J].中国电机工程学报,2013,33(25):33-40.ZHANG Xueqing,LIANG Jun,ZHANG Xi,et al.Combined model for ultra short-term wind power prediction based on sample entropy and extreme learning machine[J].Proceedings of the CSEE,2013,33(25):33-40.
[22]范剑青,姚琦伟,陈敏.非线性时间序列:建模预报及应用[M].高等教育出版社,2005,28-46.
[23]李江,王宝财,陈继开.考虑气象因素的改进虚拟交互回归负荷预测方法[J].南方电网技术,2017,11(8):72-79.LI Jiang,WANG Baocai,CHEN Jikai.Improved dummy interactive regression method for load forecasting considering meteorological factors[J].Southern Power System Technology,2017,11(8):72-79.
[24]梁智,孙国强,李虎成,等.基于VMD与PSO优化深度信念网络的短期负荷预测[J].电网技术,2018,42(2):598-606.LIANG Zhi,SUN Guoqiang,LI Hucheng,et al.Shortterm load forecasting based on VMD and PSO optimized deep belief network[J].Power System Technology,2018,42(2):598-606.
[2]黄晗,孙堃,刘达.基于随机森林的电力系统小时负荷预测研究[J].智慧电力,2018,46(5):8-14.HU ANG Han,SUN Kun,LIU Da.Hourly load forecasting of power system based on random forest[J].Smart Power,2018,46(5):8-14.
[3]PEDRO GOMES,RUI CASTRO.Wind speed and wind power forecasting using statistical models:autoregressive moving average and artificial neural networks[J].International Journal of Sustainable Energy Development,2012,1(2):41-50.
[4]CASSOLA F,BURLANDO M.Wind speed and wind energy forecast through Kalman filtering of numerical weather prediction model output[J].Applied Energy,2012,99(6):154-166.
[5]喻圣,邹红波,余凡,等.模糊神经网络在电力系统短期负荷预测中的应用[J].智慧电力,2018,46(11):88-91.YU Shen,ZOU Hongbo, YU Fan,et al.Application of fuzzy neural network in power short-term load forecasting[J].Smart Power,2018,46(1 1):88-91.
[6]李若晨,朱帆,朱永利,等.基于改进乌鸦算法和ESN神经网络的短期风电功率预测[J].电力系统保护与控制,2018,46(17):83-88.LI Ruochen,ZHU Fan,ZHU Yongli,et al.Short-term power load forecasting using recurrent neural network with restricted Boltzmann machine[J].Power System Protection and Control,2018,46(17):83-88.
[7]YAN J,LIU Y,HAN S,et al.Wind power grouping forecasts and its uncertainty analysis using optimized relevance vector machine[J].Renewable&Sustainable Energy Review,2013,27(6):613-621.
[8]张雨金,杨凌帆,葛双冶,等.基于Kmeans-SVM的短期光伏发电功率预测[J].电力系统保护与控制,2018,46(21):118-124.ZHANG Yujin,YANG Lingfan,GE Shuangye,et al.Shortterm photovoltaic power forecasting based on Kmeans algorithm and support vector machine[J].Power System Protection and Control,2018,46(21):1 18-124.
[9]王贺,胡志坚,张翌晖,等.基于IPSO-LSSVM的风电功率短期预测研究[J].电力系统保护与控制,2012,40(24):107-112.WANG He,HU Zhijian,ZHANG Yihui,et al.Shortterm prediction of wind power based on IPSO-LSSVM[J].Power System Protection and Control,2012,40(24):107-112.
[10]陶玉波,陈昊,秦晓辉,等.短期风电功率预测概念和模型与方法[J].电力工程技术,2018,37(5):7-13.TAO Yubo,CHEN Hao,QIN Xiaohui,et al.A review of the short-term wind power forecasting theory,model and approach[J].Jiangsu Electrical Engineering,2018,37(5):7-13.
[11]张亚超,刘开培,秦亮.基于VMD-SE和机器学习算法的短期风电功率多层级综合预测模型[J].电网技术,2016,40(5):1334-1340.ZHANG Yachao,LIU Kaipei,QIN Liang.Short-term wind power multi-leveled combined forecasting model based on variational mode decomposition-sample entropy and machine learning algorithms[J].Power System Technology,2016,40(5):1334-1340.
[12]ZHANG W,LIU F,ZHENG X,et al.A hybrid EMDSVM based short-term wind power forecasting model[C].Brisbane:Power and Energy Engineering Conference,IEEE,2016:1-5.
[13]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 Zhijian,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.
[14]TORRES M E,COLO MINAS M A,SCHLOTTHAUER G,et al.A comp lete ense mble empirical mode decomposition with adaptive noise[C].Acoustics:IEEE International Conference:Speech and Signal Processing,2011:4144-4147.
[15]BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[16]李青,李军,马昊.基于互补型集成经验模态分解-模糊熵和回声状态网络的短期电力负荷预测[J].计算机应用,2014,34(12):3651-3655.LI Qing,LI Jun,MA Hao.Short-term electricity load forecasting based on complementary ensemble empirical mode decomposition-fuzzy permutation and echo state network[J].Journal of Computer Applications,2014,34(12):3651-3655.
[17]潘云,张晓星,张英,等.基于互补集合经验模态分解法的变压器局部放电信号去噪方法[J].广东电力,2017,30(10):7-13.PAN Yun,ZHANG Xiaoxing,ZHANG Ying,et al.Denoising method for transformer partial discharge signals based on complete ensemble empirical mode decomposition[J].Guangdong Electric Power,2017,30(10):7-13.
[18]周涛涛,朱显明,彭伟才,等.基于CEEMD和排列熵的故障数据小波阈值降噪方法[J].振动与冲击,2015,34(23):207-211.ZHOU Taotao,ZHU Xianming,PENG Weicai,et al.A wavelet threshold denoising method for fault data based on CEEMD and permutation entropy[J].Journal of Vibration and Shock,2015,34(23):207-211.
[19]GRZEGORZ DUDEK.Short-term load forecasting using random forests[C].Warsaw:Proceedings of the 7th IEEE International Conference Intelligent Systems IS 2014,821-828.
[20]梁智,孙国强,卫志农,等.基于变量选择与高斯过程回归的短期负荷预测[J].电力建设,2017,38(2):122-128.LIANG Zhi,SUN Guoqiang,WEI Zhinong,et al.Shortterm load forecasting based on variable selection and gaussian process regression[J].Electric Power Construction,2017,38(2):122-128.
[21]张学清,梁军,张熙,等.基于样本熵和极端学习机的超短期风电功率组合预测模型[J].中国电机工程学报,2013,33(25):33-40.ZHANG Xueqing,LIANG Jun,ZHANG Xi,et al.Combined model for ultra short-term wind power prediction based on sample entropy and extreme learning machine[J].Proceedings of the CSEE,2013,33(25):33-40.
[22]范剑青,姚琦伟,陈敏.非线性时间序列:建模预报及应用[M].高等教育出版社,2005,28-46.
[23]李江,王宝财,陈继开.考虑气象因素的改进虚拟交互回归负荷预测方法[J].南方电网技术,2017,11(8):72-79.LI Jiang,WANG Baocai,CHEN Jikai.Improved dummy interactive regression method for load forecasting considering meteorological factors[J].Southern Power System Technology,2017,11(8):72-79.
[24]梁智,孙国强,李虎成,等.基于VMD与PSO优化深度信念网络的短期负荷预测[J].电网技术,2018,42(2):598-606.LIANG Zhi,SUN Guoqiang,LI Hucheng,et al.Shortterm load forecasting based on VMD and PSO optimized deep belief network[J].Power System Technology,2018,42(2):598-606.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |