Graph Neural Networks in Wind Power Forecasting

TL;DR

This paper explores the use of Graph Neural Networks for wind power forecasting, demonstrating their competitive performance with CNNs on multi-year data from multiple facilities.

Contribution

It is the first to evaluate GNNs for wind energy forecasting using real-world data across multiple sites and forecast horizons.

Findings

GNNs achieved performance comparable to CNN benchmarks.

GNNs effectively utilized NWP variables as predictors.

Study validated GNN applicability in real-world wind forecasting scenarios.

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.