针对对于风能规划和应用都具有重大影响的风速存在强随机性问题,该文提出结合卷积神经网络（CNN）和共享权重长短期记忆网络（SWLSTM）的空时融合模型（CSWLSTM）,充分提取风速序列中蕴含的空域和时域信息,以提升预测精度。此外,为了获得可靠的风速概率预测结果,提出一种新的结合CNN、SWLSTM和高斯过程回归（GPR）的混合模型,称为 CSWLSTM-GPR。将CSWLSTM-GPR应用于中国内蒙古风速预测案例,从点预测精度、区间预测适用性和概率预测综合性能3个方面与相同结构的CNN和SWLSTM模型的风速预测方法进行比较。CSWLSTM-GPR的可靠性测试保证了预测结果的可靠性和说服力。实验结果表明,CSWLSTM-GPR在风速预测问题上能获得高精度的点预测、合适的预测区间和可靠的概率预测结果,也充分展现了该研究所提出CSWLSTM在风速预测方面具有较好的应用潜力。
Abstract
In view of the strong randomness of wind speed in wind energy, it is difficult for wind power to be connected to the grid, reliable and high-quality wind speed prediction results are very important issues for the planning and application of wind energy. In this research, a spatio-temporal fusion model （CSWLSTM） combining convolutional neural network （CNN） and shared weight long short-term memory network （SWLSTM） is proposed to fully extract the spatial and temporal information contained in the wind speed sequence to improve prediction accuracy. In addition, in order to obtain reliable wind speed probability prediction results, a new hybrid model integrating CNN, SWLSTM and GPR is proposed, called CSWLSTM-GPR. CSWLSTM-GPR is applied to the case of wind speed prediction in Inner Mongolia, China. Comparing the wind speed prediction methods of CNN and SWLSTM models with the same structure in terms of point prediction accuracy, interval prediction applicability and comprehensive performance of probability prediction. The reliability test of CSWLSTM-GPR ensures the reliability and persuasiveness of the predicted results. The experimental results show that CSWLSTM-GPR can obtain high-precision point prediction, appropriate prediction interval and reliable probability prediction results in the wind speed prediction problem. It also fully demonstrates that the CSWLSTM proposed by this research has good application potential in wind speed prediction.
关键词
风电 /
深度学习 /
长短时记忆 /
区间预测 /
概率预测 /
风速预测
Key words
wind power /
deep learning /
long short-term memory /
interval prediction /
probability prediction /
wind speed forecast
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] REN Y, SUGANTAHN P N, SRIKANTH N.A novel empirical mode decomposition with support vector regression for wind speed forecasting[J]. IEEE transactions on neural networks and learning systems, 2016, 27(8): 1793-1798.
[2] TASNIM S, RAHMAN A, OO A, et al.Wind power prediction in new stations based on knowledge of existing stations: a cluster based multi source domain adaptation approach[J]. Knowledge-based systems, 2018, 145: 15-24.
[3] YUAN X H, TAN Q X, LEI X H, et al.Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine[J]. Energy, 2017, 129: 122-137.
[4] ZHANG J, DRAXL C, HOPSON T, et al.Comparison of numerical weather prediction based deterministic and probabilistic wind resource assessment methods[J]. Applied energy, 2015, 156(11): 528-541.
[5] ALLEN D J, TOMLIN A S, BALE C, et al.A boundary layerscaling technique for estimating near-surface wind energy using numerical weather prediction and wind map data[J]. Applied energy, 2017, 208: 1246-1257.
[6] WANG J J, LI Y N.Multi-step ahead wind speed prediction based on optimal feature extraction, long short term memory neural network and error correction strategy[J]. Applied energy, 2018, 230: 429-443.
[7] ERDEM E, JING S.ARMA based approaches for forecasting the tuple of wind speed and direction[J]. Applied energy, 2011, 88(4): 1405-1414.
[8] ARIAS J.Exact maximum likelihood estimation of stationary vector ARMA models[J]. Journal of the American Statistical Association, 1995, 90(429): 282-291.
[9] ZHANG C, WEI H K, ZHAO X, et al.A Gaussian process regression based hybrid approach for short-term wind speed prediction[J]. Energy conversion and management, 2016, 126: 1084-1092.
[10] CHEN K L, YU J.Short-term wind speed prediction using an unscented Kalman filter based state-space support vector regression approach[J]. Applied energy, 2014, 113: 690-705.
[11] NIELSEN H A, MADSEN H, NIELSEN T S.Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts[J]. Wind energy, 2006, 9(1-2): 95-108.
[12] FINAMORE A R, CALDERARO V, GALDI V, et al.A wind speed forecasting model based on artificial neural network and meteorological data[C]//16 IEEE International Conference on Environment and Electrical Engineering(EEEIC), Florence, Italy, 2016.
[13] HU Q H, ZHANG S G, XIE Z X, et al.Noise model based ν-support vector regression with its application to short-term wind speed forecasting[J]. Neural networks, 2014, 57: 1-11.
[14] REN C, AN N, WANG J Z, et al.Optimal parameters selection for BP neural network based on particle swarm optimization: a case study of wind speed forecasting[J]. Knowledge-based systems, 2014, 56: 226-239.
[15] WANG L L, LI X, BAI Y L.Short-term wind speed prediction using an extreme learning machine model with error correction[J]. Energy conversion and management, 2018, 162: 239-250.
[16] LIU H, TIAN H Q, LI Y F.Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction[J]. Applied energy, 2012, 98: 415-424.
[17] KHOSRAVI A, KOURY R, MACHADO L, et al.Prediction of wind speed and wind direction using artificial neural network, support vector regression and adaptive neuro-fuzzy inference system[J]. Sustainable energy technologies and assessments, 2018, 25: 146-160.
[18] ZHANG C, WEI H K, ZHAO J S, et al.Short-term wind speed forecasting using empirical mode decomposition and feature selection[J]. Renewable energy, 2016, 96: 727-737.
[19] KIPLANGAT D C, ASOKAN K, KUMAR K S.Improved week-ahead predictions of wind speed using simple linear models with wavelet decomposition[J]. Renewable energy, 2016, 93: 38-44.
[20] LI X Y, YI X H, LIU Z H, et al.Application of novel hybrid deep leaning model for cleaner production in a paper industrial wastewater treatment system[J]. Journal of cleaner production, 2021(294): 126-134.
[21] EHSAN M A, SHAHIRINIA A, ZHANG N, et al.Wind speed prediction and visualization using long short-term memory networks (LSTM)[J]. arXiv: 2005.12401.
[22] BOULILA W, GHANDORH H, KHAN M, et al.A novel CNN-LSTM-based approach to predict urban expansion[J]. Ecological informatics, 2021, 23(5): 325-332.
[23] DEY R, SALEM F M.Gate-variants of gated recurrent unit (GRU) neural networks[C]//2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), Boston, MA, USA, 2017.
[24] PEI S Q, QIN H, ZHANG Z D, et al.Wind speed prediction method based on empirical wavelet transform and new cell update long short-term memory network[J]. Energy conversion and management, 2019, 196: 779-792.
[25] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6): 1229-1251.
ZHOU F Y, JIN L P, DONG J.Review of convolutional neural network[J]. Chinese journal of computers, 2017, 40(6): 1229-1251.
[26] 李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述[J]. 计算机应用, 2016, 36(9): 2508-2515.
LI Y D, HAO Z B, LEI H.Survey of convolutional neural network[J]. Journal of computer applications, 2016, 36(9): 2508-2515.
[27] LECUN Y.LeNet-5, convolutional neural networks[EB/OL]. http://yann.lecun. com/exdb/lenet.
[28] ZHANG R L, ZONG Q, DOU L Q, et al.A novel hybrid deep learning scheme for four-class motor imagery classification[J]. Journal of neural engineering, 2019, 16(6): 174-185.
[29] HE K M, ZHANG X Y, REN S Q, et al.Delving deep into rectifiers: surpassing human-level performance on imagenet classification[C]//Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 2015.
[30] SAXE A M, MCCLELLAND J L, GANGULI S.Exact solutions to the nonlinear dynamics of learning in deep linear neural networks[J]. arXiv: 2013.6120 .
[31] CHANG Z H, ZHANG Y, CHEN W B.Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform[J]. Energy, 2019, 187: 115-126.
[32] 尹宝才, 王文通, 王立春. 深度学习研究综述[J]. 北京工业大学学报, 2015, 41(1): 48-59.
YIN B C, WANG W T, WANG L C.Review of deep learning[J]. Journal of Beijing University of Technology, 2015, 41(1): 48-59.
PDF(2373 KB)
