Wind Farm Forecasting Based on MLSTM
Journal of Computer Science and Digital Technology · 2025
DOI: 10.71204/rpvp8658 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science and Digital Technology, 2025. Verfasst von Peng Zhao und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Zhao, P., Yang, J., & Zhang, S. (2025). Wind Farm Forecasting Based on MLSTM. Journal of Computer Science and Digital Technology. https://doi.org/10.71204/rpvp8658
Vancouver
Zhao P, Yang J, Zhang S. Wind Farm Forecasting Based on MLSTM. Journal of Computer Science and Digital Technology. 2025. doi:10.71204/rpvp8658
BibTeX
@article{Zhao2025,
author = {Zhao, Peng and Yang, Junye and Zhang, Senhao},
title = {Wind Farm Forecasting Based on MLSTM},
journal = {Journal of Computer Science and Digital Technology},
year = {2025},
doi = {10.71204/rpvp8658}
}
EUVIMED