Optimization and Accuracy Improvement of Power Forecasting Models for Wind Farms Under Transient Weather Conditions
Main Article Content
Abstract
Given the problems of non-stationary power time series, response lag, and amplified prediction errors due to sudden changes in wind direction under transitional meteorological conditions, this study proposes a wind power forecasting model that integrates multiscale time-series features, transition-aware attention mechanisms, physical constraints on turbine operation, and dynamic residual correction. To improve the model's ability to jointly characterize different scales of meteorological evolution and power lag characteristics, a feature extraction network with short-, medium-, and long-term branches based on TCN (Temporal Convolutional Network) is built, which incorporates bidirectional GRU and Transformer architectures; additionally, the feature weights at each scale are dynamically adjusted according to the severity of inflection points, and the prediction output is constrained by air density, power curves, operational status and ramping limits. Residual caching and time-delay gating are employed to correct for lag errors in the range of 1 to 6 sampling steps. 50,842 valid data sets from a wind farm were used for validation. The general MAE and RMSE of the model were 0.258 MW and 0.386 MW, respectively, and these were lower than those of the baseline TCN by 21.58% and 20.90%. In the transition period, the MAE and RMSE were 0.305 MW and 0.448 MW; these had been reduced by 22.19% and 23.29%. Therefore, the developed model can reduce peak deviations caused by abrupt changes in weather and improve the accuracy and stability of wind power forecasting under all operating conditions.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
E. Ammar and G. Xydis, “Wind speed forecasting using deep learning and preprocessing techniques,” International journal of Green energy, vol. 21, no. 5, pp. 988–1016, 2024.
J. Jamii, M. Trabelsi, M. Mansouri, et al., “Medium-term wind power forecasting using reduced principal component analysis based random forest model,” Wind Engineering, vol. 48, no. 4, pp. 597–616, 2024.
A. G. Rangaraj, Y. Srinath, K. Boopathi, et al., “Statistical post-processing of numerical weather prediction data using distribution-based scaling for wind energy,” Wind engineering, vol. 48, no. 5, pp. 824–834, 2024.
J. Parmar and J. Pieper, “A radial basis function neural network approach to filtering stochastic wind speed data,” Wind Engineering, vol. 48, no. 1, pp. 15–31, 2024.
K. Kumar, P. Prabhakar, and A. Verma, “Forecasting wind power using Optimized Recurrent Neural Network strategy with time-series data,” Optimal Control Applications and Methods, vol. 45, no. 4, pp. 1798–1814, 2024.
S. Mulewa, A. Parmar, and A. de, “A novel Bagged-CNN architecture for short-term wind power forecasting,” International Journal of Green Energy, vol. 21, no. 12, pp. 2712–2723, 2024.
Y. Akbal and K. D. Ünlü, “A hybrid deep learning methodology for wind power forecasting based on attention,” International Journal of Green Energy, vol. 21, no. 16, pp. 3713–3722, 2024.
M. Lydia, G. Edwin Prem Kumar, and R. Akash, “Wind speed and wind power forecasting models,” Energy & Environment, vol. 36, no. 8, pp. 3677–3713, 2025.
D. Bouabdallaoui, T. Haidi, M. Derri, et al., “Multi-temporal forecasting of wind energy production using artificial intelligence models,” International Journal of Renewable Energy Development, vol. 14, no. 3, pp. 505–517, 2025.
M. A. Yassen, E. S. M. El-Kenawy, M. G. Abdel-Fattah, et al., “Explainable artificial intelligence for wind power forecasting model based on long short-term memory,” Neural Computing and Applications, vol. 37, no. 19, pp. 14589–14611, 2025.
T. A. Rajaperumal and C. Christopher Columbus, “Enhanced wind power forecasting using machine learning, deep learning models and ensemble integration,” Scientific Reports, vol. 15, no. 1, p. 20572, 2025.
A. Pierrot and P. Pinson, “Data Are Missing Again—Reconstruction of Power Generation Data Using k k-Nearest Neighbors and Spectral Graph Theory,” Wind Energy, vol. 28, no. 1, p. e2962, 2025.
A. Durap, “Explainable deep learning techniques for wind speed forecasting in coastal areas: Integrating model configuration, regularization, early stopping, and SHAP analysis,” Neural Computing and Applications, vol. 37, no. 25, pp. 21219–21257, 2025.
N. Dmitrijevs, V. Komasilovs, S. Orlova, et al., “Short-term wind energy yield forecasting: A comparative analysis using multiple data sources,” Energies, vol. 18, no. 16, p. 4393, 2025.
E. A. Manzano, R. E. Nogales, and A. Rios, “A Systematic Review of Wind Energy Forecasting Models Based on Deep Neural Networks,” Wind, vol. 5, no. 4, p. 29, 2025.
I. U. Haq, A. Kumar, and P. S. Rathore, “Machine learning approaches for wind power forecasting: a comprehensive review,” Discover Applied Sciences, vol. 7, no. 10, p. 1139, 2025.
B. Amarzaya and K. Ko, “Influence of missing wind measurements on wind turbine power production using various measure-correlate-predict methods and reanalysis datasets,” International Journal of Renewable Energy Development, vol. 14, no. 6, pp. 1213–1220, 2025.
G. Dantas and J. Browell, “Seamless Short-to Mid-Term Probabilistic Wind Power Forecasting,” Wind Energy, vol. 29, no. 2, p. e70079, 2026.
M. Bernabe, E. Cadenas, E. Lopez-Espinoza, et al., “Hybrid WRF– SARIMA model to improve day-ahead wind speed forecast accuracy,” International Journal of Renewable Energy Development, vol. 15, no. 1, pp. 76–88, 2026.
G. ¸Sahin, F. Kürker, A. Nur, et al., “Short-Term Wind Speed Forecasting Using Leakage-Free Time-Series Modeling and Statistical Residual Evaluation,” Sustainability, vol. 18, no. 11, p. 5623, 2026.
S. M. R. Hussain, M. M. A. Baig, and M. U. Yousuf, “DVTransformer: A novel approach for multi-step wind power forecasting using spatio-temporal dynamics and predictive strategies,” AIMS Energy, vol. 14, no. 2, pp. 387–417, 2026.
T. L. Nguyen, N. K. Vy, M. Y. Nguyen, et al., “WindFusion-EW: An Ensemble-Weighted Multi-Model Framework for Ultra-Short-Term Wind Power Forecasting,” Engineering, Technology & Applied Science Research, vol. 16, no. 2, pp. 33925–33930, 2026.
B. Karaca, K. D. Ünlü, and S. Türkan, “Wavelet-enhanced sequence-to-sequence modeling with attention mechanism for short-term wind power forecasting,” Cybernetics and Systems, vol. 57, no. 3, pp. 485–533, 2026.