Medium-and long-term wind speed prediction using the multi-task learning paradigm
A. Gómez-Orellana, V. Vargas, D. Guijo-Rubio , J. Pérez-Aracil, P. Gutiérrez, S. Salcedo-Sanz, C. Hervás-Martínez
International work-conference on the interplay between natural and artificial computation, pp. 1-10, 2024Abstract
Renewable energies, particularly wind energy, have gain significant attention due to their clean and inexhaustible nature. Despite their commendable efficiency and minimal environmental impact, wind energy faces challenges such as stochasticity and intermittence. Machine learning methods offer a promising avenue for mitigating these challenges, particularly through wind speed prediction, which is crucial for optimising wind turbine performance. One important aspect to consider, regardless of the methodology employed and the approach used to tackle the wind speed prediction problem, is the prediction horizon. Most of the works in the literature have been designed to deal with a single prediction horizon. However, in this study, we propose a multi-task learning framework capable of simultaneously handling various prediction horizons. For this purpose, Artificial Neural Networks (ANNs) are considered, specifically a multilayer perceptron. Our study focuses on medium- and long-term prediction horizons (6 h, 12 h, and 24 h ahead), using wind speed data collected over ten years from a Spanish wind farm, along with ERA5 reanalysis variables that serve as input for the wind speed prediction. The results obtained indicate that the proposed multi-task model performing the three prediction horizons simultaneously can achieve comparable performance to corresponding single-task models while offering simplicity in terms of lower complexity, which includes the number of neurons and links, as well as computational resources.
Cite this publication
BibTex
@inproceedings{gomez-orellana2024medium-and,
author = {Antonio Manuel Gómez-Orellana and Víctor Manuel Vargas and David Guijo-Rubio and Jorge Pérez-Aracil and Pedro Antonio Gutiérrez and Sancho Salcedo-Sanz and César Hervás-Martínez},
title = {Medium-and long-term wind speed prediction using the multi-task learning paradigm},
booktitle = {International work-conference on the interplay between natural and artificial computation},
year = {2024},
pages = {1--10},
doi = {10.1007/978-3-031-61137-7_27}
}
APA
Gómez-Orellana, A., Vargas, V., Guijo-Rubio, D., Pérez-Aracil, J., Gutiérrez, P., Salcedo-Sanz, S., Hervás-Martínez, C. (2024). Medium-and long-term wind speed prediction using the multi-task learning paradigm. In International work-conference on the interplay between natural and artificial computation (pp. 1-10).
CV
A.M. Gómez-Orellana, V.M. Vargas, D. Guijo-Rubio (CA), J. Pérez-Aracil, P.A. Gutiérrez, S. Salcedo-Sanz, C. Hervás-Martínez, (2/7) "Medium-and long-term wind speed prediction using the multi-task learning paradigm". International work-conference on the interplay between natural and artificial computation, pp. 1-10, 2024.
RIS
TY - CONF T1 - Medium-and long-term wind speed prediction using the multi-task learning paradigm T2 - International work-conference on the interplay between natural and artificial computation AU - Gómez-Orellana, Antonio Manuel AU - Vargas, Víctor Manuel AU - Guijo-Rubio, David AU - Pérez-Aracil, Jorge AU - Gutiérrez, Pedro Antonio AU - Salcedo-Sanz, Sancho AU - Hervás-Martínez, César JO - International work-conference on the interplay between natural and artificial computation JA - International work-conference on the interplay between natural and artificial computation Y1 - 2024 PY - 2024 SP - 1 EP - 10 DO - 10.1007/978-3-031-61137-7_27 ER -