Amid the randomness and volatility of wind speed, an improved VMD-BP-CNN-LSTM model for
short-term wind speed prediction was proposed to assist in power system
planning and operation in this paper. Firstly, the wind speed time series data
was processed using Variational Mode Decomposition (VMD) to obtain multiple frequency components. Then, each individual frequency
component was channeled into a combined prediction framework consisting of BP neural network (BPNN), Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM)
after the execution of differential and normalization operations. Thereafter,
the predictive outputs for each component underwent integration through a
fully-connected neural architecture for data fusion processing, resulting in
the final prediction. The VMD decomposition technique was introduced in a
generalized CNN-LSTM prediction model; a BPNN model was utilized to predict high-frequency components obtained from VMD, and
incorporated a fully connected neural network for data fusion of individual
component predictions. Experimental results demonstrated that the proposed
improved VMD-BP-CNN-LSTM model outperformed other combined prediction models in terms of prediction accuracy, providing a solid foundation for optimizing the
safe operation of wind farms.
References
[1]
Ko, M.-S., Lee, K., Kim, J.-K., Hong, C.W., Dong, Z.Y. and Hur, K. (2021) Deep Concatenated Residual Network with Bidirectional LSTM for One-Hour-Ahead Wind Power Forecasting. IEEE Transactions on Sustainable Energy, 12, 1321-1335. https://doi.org/10.1109/TSTE.2020.3043884
[2]
Li, M., Yang, M., Yu, Y. and Lee, W.-J. (2022) A Wind Speed Correction Method Based on Modified Hidden Markov Model for Enhancing Wind Power Forecast. IEEE Transactions on Industry Applications, 58, 656-666. https://doi.org/10.1109/TIA.2021.3127145
[3]
Liu, F., Li, H.D. and Tan, T. (2023) Short-Term Wind Power Prediction Based on CEEMDAN-AsyHyperBand-MultiTCN. Acta Energiae Solaris Sinica, 1-8. (In Chinese) https://doi.org/10.19912/j.0254-0096.tynxb.2022-1427
[4]
Catalão, J.P.S., Pousinho, H.M.I. and Mendes, V.M.F. (2011) Short-Term Wind Power Forecasting in Portugal by Neural Networks and Wavelet Transform. Renewable Energy, 36, 1245-1251. https://doi.org/10.1016/j.renene.2010.09.016
[5]
Tan, M., Yuan, S., Li, S., Su, Y., Li, H. and He, F. (2020) Ultra-Short-Term Industrial Power Demand Forecasting Using LSTM Based Hybrid Ensemble Learning. IEEE Transactions on Power Systems, 35, 2937-2948. https://doi.org/10.1109/TPWRS.2019.2963109
[6]
Lu, C., Wang, Z., Wu, Z., Zheng, Y. and Liu, Y. (2023) Global Ocean Wind Speed Retrieval from GNSS Reflectometry Using CNN-LSTM Network. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-12. https://doi.org/10.1109/TGRS.2023.3276173
[7]
Li, R., Ma, T., Zhang, X., et al. (2021) Short-Term Wind Power Prediction Based on Convolutional Long Short-Term Memory Neural Network. Acta Energiae Solaris Sinica, 42, 304-311. (In Chinese)
[8]
Wang, Y.X., Liu, E.J. and Huan, Y.Z. (2022) Ultra-Short-Term Wind Power Prediction Method Based on CNN-LSTM-LightGBM Combination. Science Technology and Engineering, 22, 16067-16074. (In Chinese)
[9]
Zhang, G., Xu, B., Liu, H., Hou, J. and Zhang, J. (2021) Wind Power Prediction Based on Variational Mode Decomposition and Feature Selection. Journal of Modern Power Systems and Clean Energy, 9, 1520-1529. https://doi.org/10.35833/MPCE.2020.000205
[10]
Qin, B., Huang, X., Wang, X., et al. (2023) Ultra-Short-Term Wind Power Prediction Based on Double Decomposition and LSSVM. Transactions of the Institute of Measurement and Control, 45, 2627-2636. https://doi.org/10.1177/01423312231153258
[11]
Wang, T.T., Lu, Y.M. and Liu, T.Z. (2023) Storm Surge Prediction Based on VMD-CNN-LSTM Model and Transfer Learning Framework. Journal of Catastrophology, 38, 195-202. (In Chinese) https://kns.cnki.net/kcms2/article/abstract?v=fCqJ37DMrBnose4V9bkCrlv1sh1JWXUog5wNFP0uPBTkxw6wO78rP20B7oflPvfNkf2cf9Ef--EEvbWzfo4CfrO2MwQMIEI3KLPstX2vXM1C5da7NzGvJNafUC89sJelQPiHaXSxasu_qUS_ljpAPA==&uniplatform=NZKPT&language=CHS
[12]
Lv, L., Wu, Z., Zhang, J., Zhang, L., Tan, Z. and Tian, Z. (2022) A VMD and LSTM Based Hybrid Model of Load Forecasting for Power Grid Security. IEEE Transactions on Industrial Informatics, 18, 6474-6482. https://doi.org/10.1109/TII.2021.3130237
[13]
Li, S.S., Ma, X.J., Pan, L.X., et al. (2023) Research on Short-Term Load Forecasting Model Based on VMD and LSTM-CNN. Control Engineering of China, 30, 469-478. (In Chinese)
[14]
Tao, K., Wu, D.H. and Pan, L.X. (2021) Short-Term Wind Power Prediction Based on VMD-JAYA-LSSVM. Control Engineering of China, 28, 1143-1149. (In Chinese)
[15]
Jalali, S.M.J., Ahmadian, S., Kavousi-Fard, A., Khosravi, A. and Nahavandi, S. (2022) Automated Deep CNN-LSTM Architecture Design for Solar Irradiance Forecasting. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52, 54-65. https://doi.org/10.1109/TSMC.2021.3093519
[16]
Yin, X. and Zhao, X. (2021) Deep Neural Learning Based Distributed Predictive Control for Offshore Wind Farm Using High-Fidelity LES Data. IEEE Transactions on Industrial Electronics, 68, 3251-3261. https://doi.org/10.1109/TIE.2020.2979560
[17]
Wang, W., Zhu, Q., Wang, Z., Zhao, X. and Yang, Y. (2022) Research on Indoor Positioning Algorithm Based on SAGA-BP Neural Network. IEEE Sensors Journal, 22, 3736-3744. https://doi.org/10.1109/JSEN.2021.3120882
[18]
Yu, Q., Zhang, Y.D., Guo, J., et al. (2023) Short-Term Inbound Passenger Flow Forecasting for Urban Rail Transit Based on Deep Ensemble Neural Networks. Journal of the China Railway Society, 45, 37-46. (In Chinese)