Wind Farm Forecasting Based on MLSTM
DOI:
https://doi.org/10.71204/rpvp8658Keywords:
Wind Power Prediction, Wind Speed, LSTM, mLSTM, Time Series PredictionAbstract
With the increasing importance of wind energy in the global energy structure, wind power forecasting has become one of the key technologies to ensure grid stability and improve energy dispatch efficiency. This paper uses the wind speed and wind power data of US wind farms in 2012 to predict and compare wind speed and wind power of different LSTM variant models (including traditional LSTM, xLSTM, sLSTM and mLSTM) by sampling every 5 minutes. The research focuses on comparing the performance of each model in predicting wind speed under the same power output conditions. The experimental results are evaluated by three common evaluation indicators: MAE , MSE and R². The results show that the mLSTM model performs best in wind speed forecasting, with better accuracy and stability than other LSTM variants. The research in this paper provides a new method to improve the accuracy of wind power forecasting and provides effective decision support for the operation and management of wind farms.
References
Duque, Á. J., Castronuovo, E. D., Sánchez, I., & Usaola, J. (2011). Optimal operation of a pumped-storage hydro plant that compensates the imbalances of a wind power producer. Electric power systems research, 81(9), 1767-1777.
Foley, A. M., Leahy, P. G., Marvuglia, A., & McKeogh, E. J. (2012). Current methods and advances in forecasting of wind power generation. Renewable energy, 37(1), 1-8.
Lungu, I., Căruțașu, G., Pirjan, A., Oprea, S. V., & Bara, A. (2016). A two-step forecasting solution and upscaling technique for small size wind farms located in hilly areas of Romania. Studies in Informatics and Control, 25(1), 77-86.
Wessel, A., Stock, S., & von Bremen, L. (2017). Wind, the Wild Boy in the Power Plant Family: How Grid Integration of Offshore Wind Farms is Achieved. Sea–Wind–Power: Research at the first German offshore wind farm Alpha Ventus, 171-186.
Medved, D., Conka, Z., Pavlik, M., Zbojovsky, J., Kolcun, M., & Ivancak, M. (2019). Prediction of electricity production in island operation under the different wind generation modes. Przeglad Elektrotechniczny, 95(7), 150-154.
Ghoushchi, S. J., Manjili, S., Mardani, A., & Saraji, M. K. (2021). An extended new approach for forecasting short-term wind power using modified fuzzy wavelet neural network: A case study in wind power plant. Energy, 223, 120052.
Pang, S., Zheng, Z., Luo, F., Xiao, X., & Xu, L. (2021). Hybrid forecasting methodology for wind power-photovoltaic-concentrating solar power generation clustered renewable energy systems. Sustainability, 13(12), 6681.
Wang, Z., Zhang, B., Mobtahej, M., Baziar, A., & Khan, B. (2021). Advanced reactive power compensation of wind power plant using PMU data. IEEE Access, 9, 67006-67014.
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to forget: Continual prediction with LSTM. Neural computation, 12(10), 2451-2471.
Yuan, F., Huang, X., Zheng, L., Wang, L., Wang, Y., Yan, X., Gu, S., & Peng, Y. (2025). The Evolution and Optimization Strategies of a PBFT Consensus Algorithm for Consortium Blockchains.Information,16(4), 268. https://doi.org/10.3390/info16040268
Huang, Z., Xu, W., & Yu, K. (2015). Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991.
Zhou, C., Sun, C., Liu, Z., & Lau, F. (2015). A C-LSTM neural network for text classification. arXiv preprint arXiv:1511.08630.
Graves, A., & Schmidhuber, J. (2005). Framewise phoneme classification with bidirectional LSTM networks. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 4, 2047-2052.
Liu, Z., Gao, W., Wan, Y. H., & Muljadi, E. (2012). Wind power plant prediction by using neural networks. In 2012 IEEE energy conversion congress and exposition (ECCE), 3154-3160.
Wang, Y., Huang, M., Zhu, X., & Zhao, L. (2016). Attention-based LSTM for aspect-level sentiment classification. In Proceedings of the 2016 conference on empirical methods in natural language processing, 606-615.
Wang, F., Jiang, J., & Zhang, L. (2021). Research on Ultra-Short-Term Wind Power Forecasting Based on Refactored Representation of Environmental Features. In IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 375-379.
Downloads
Published
Data Availability Statement
This dataset comes from the "United States Wind Farm Data - 2012". The original contributions presented in this study are included in the article. Further inquiries can be directed to the corresponding author(s).
Issue
Section
License
Copyright (c) 2025 Journal of Computer Science and Digital Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.