Graph Neural Networks in Wind Power Forecasting

Javier Castellano; Ignacio Villanueva

Graph Neural Networks in Wind Power Forecasting

Machine Learning 2025-07-02 v1 Systems and Control Systems and Control

Authors: Javier Castellano , Ignacio Villanueva

Abstract

We study the applicability of GNNs to the problem of wind energy forecasting. We find that certain architectures achieve performance comparable to our best CNN-based benchmark. The study is conducted on three wind power facilities using five years of historical data. Numerical Weather Prediction (NWP) variables were used as predictors, and models were evaluated on a 24 to 36 hour ahead test horizon.

Keywords

solar energy forecasting graph neural network time series forecasting

Cite

@article{arxiv.2507.00105,
  title  = {Graph Neural Networks in Wind Power Forecasting},
  author = {Javier Castellano and Ignacio Villanueva},
  journal= {arXiv preprint arXiv:2507.00105},
  year   = {2025}
}

Related papers

View all related →