Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning

R. Ayllón-Gavilán, A. Gómez-Orellana, V. Vargas , D. Guijo-Rubio, J. Pérez-Aracil, S. Salcedo-Sanz, P. Gutiérrez, C. Hervás-Martínez

Integrated Computer-Aided Engineering, pp. 1-13, 2025 Indexed in JCR. Impact factor: 5.8, Position: 13/181 (Q1D1) in ENGINEERING, MULTIDISCIPLINARY

Abstract

In this paper, we present the MUSONet model, which leverages information from different sources (in this case, wind farms) to perform a multi-step wind speed prediction. The main goal of this approach is improving the global prediction accuracy, specifically at longer prediction horizons. Thus, the proposed model is able to simultaneously predict the wind speed at three different prediction horizons (6h, 12h, and 24h), across three different wind farms located in Spain. We also evaluate the performance of the presented methodology by considering three different activation functions for hidden neurons in the neural network: Sigmoid, ReLU, and ELUs+2L. The results show that the proposed multi-source approach improves the performance of the single-source counterpart for the longer prediction horizons (12h and 24h). In addition, the proposed multi-source method reduces by over 30% the number of parameters compared to three single-source models (in this case, one model per wind farm), resulting in a simpler solution for the problem addressed and requiring much lower computational resources.

Cite this publication
BibTex 
@article{ayllon-gavilan2025simultaneous,
    author = {Rafael Ayllón-Gavilán and Antonio Manuel Gómez-Orellana and Víctor Manuel Vargas and David Guijo-Rubio and Jorge Pérez-Aracil and Sancho Salcedo-Sanz and Pedro Antonio Gutiérrez and César Hervás-Martínez},
    title = {Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning},
    journal = {Integrated Computer-Aided Engineering},
    year = {2025},
    volume = {null},
    number = {null},
    pages = {1--13},
    doi = {10.1177/10692509251337224}
}
APA 
Ayllón-Gavilán, R., Gómez-Orellana, A., Vargas, V., Guijo-Rubio, D., Pérez-Aracil, J., Salcedo-Sanz, S., Gutiérrez, P., Hervás-Martínez, C. (2025). Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning. Integrated Computer-Aided Engineering, null(null), 1-13.
CV 
R. Ayllón-Gavilán, A.M. Gómez-Orellana, V.M. Vargas (CA), D. Guijo-Rubio, J. Pérez-Aracil, S. Salcedo-Sanz, P.A. Gutiérrez, C. Hervás-Martínez, (3/8) "Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning", Integrated Computer-Aided Engineering, Vol. null(null), pp. 1-13, 2025. (Q1, D1, IF: 5.8)
RIS 
TY  - JOUR
T1  - Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning
AU  - Ayllón-Gavilán, Rafael
AU  - Gómez-Orellana, Antonio Manuel
AU  - Vargas, Víctor Manuel
AU  - Guijo-Rubio, David
AU  - Pérez-Aracil, Jorge
AU  - Salcedo-Sanz, Sancho
AU  - Gutiérrez, Pedro Antonio
AU  - Hervás-Martínez, César
JO  - Integrated Computer-Aided Engineering
VL  - null
IS  - null
SP  - 1
EP  - 13
PY  - 2025
DO  - 10.1177/10692509251337224
ER  -