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

Research areas:

• Uncategorized

Year:

2025

Type of Publication:

Article

Keywords:

Multi-task algorithms, deep neural networks, wind speed prediction, wind farms

Authors:

• Ayllón-Gavilán, Rafael
• Gómez-Orellana, Antonio Manuel
• Vargas, Víctor Manuel
• Guijo-Rubio, David
• Pérez-Aracil, Jorge
• Salcedo-Sanz, Sancho
• Gutiérrez, Pedro Antonio
• Hervás-Martínez, César

Journal:

Integrated Computer-Aided Engineering

Volume:

Accepted

Pages:

1-13

Month:

Mayo

ISSN:

1069-2509

Note:

JCR(2024): 5.3, Position: 22/175 (Q1) Category: 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.

Comments:

JCR(2024): 5.3, Position: 22/175 (Q1) Category: ENGINEERING, MULTIDISCIPLINARY