Enhancing Wind Power Forecasting in the Spanish Market Through Transformer Neural Networks and Temporal Optimization

T. Oriol, J. Cifuentes, G. Marulanda

Sustainability Vol. 17, nº. 19, pp. 8655

Summary:

The increasing penetration of renewable energy, and wind power in particular, requires accurate short-term forecasting to ensure grid stability, reduce operational uncertainty, and facilitate large-scale integration of intermittent resources. This study evaluates Transformer-based architectures for wind power forecasting using hourly generation data from Spain (2020–2024). Time series were segmented into input windows of 12, 24, and 36 h, and multiple model configurations were systematically tested. For benchmarking, LSTM and GRU models were trained under identical protocols. The results show that the Transformer consistently outperformed recurrent baselines across all horizons. The best configuration, using a 36 h input sequence with moderate dimensionality and shallow depth, achieved an RMSE of 370.71 MW, MAE of 258.77 MW, and MAPE of 4.92%, reducing error by a significant margin compared to LSTM and GRU models, whose best performances reached RMSEs above 395 MW and MAPEs above 5.7%. Beyond predictive accuracy, attention maps revealed that the Transformer effectively captured short-term fluctuations while also attending to longer-range dependencies, offering a transparent mechanism for interpreting the contribution of historical information to forecasts. These findings demonstrate the superior performance of Transformer-based models in short-term wind power forecasting, underscoring their capacity to deliver more accurate and interpretable predictions that support the reliable integration of renewable energy into modern power systems.

Spanish layman's summary:

Este estudio evalúa Transformers para predecir generación eólica en España (2020–2024). Superan a LSTM y GRU en precisión, con un MAPE del 4,92%. Usando secuencias de 36 h, capturan mejor fluctuaciones y dependencias, mejorando la integración renovable en la red. 

English layman's summary:

This study evaluates Transformers for wind power forecasting in Spain (2020–2024). They outperform LSTM and GRU, achieving a 4.92% MAPE. Using 36 h input windows, they better capture fluctuations and dependencies, enhancing renewable integration into the power grid.

Keywords: wind power forecasting; transformer models; deep learning; short-term forecasting; renewable energy integration; sustainable energy systems

JCR-JIF Impact Factor and WoS quartile: 4,100 - Q2 (2025)

DOI reference: https://doi.org/10.3390/su17198655

Published on paper: October 2025.

Published on-line: September 2025.

Citation:
T. Oriol, J. Cifuentes, G. Marulanda, "Enhancing Wind Power Forecasting in the Spanish Market Through Transformer Neural Networks and Temporal Optimization", Sustainability, Vol. 17, nº. 19, pp. 8655, October 2025. [Online: September 2025] doi: 10.3390/su17198655