GSTAformer: graph-guided spatio-temporal autoformer for mid-term wind power forecasting

Yuan, S. ORCID: https://orcid.org/0009-0008-2792-9772, Mao, Y. ORCID: https://orcid.org/0009-0007-9967-6770, Tian, C., Yu, F., Guo, T. and Xia, M. ORCID: https://orcid.org/0000-0003-4681-9129 (2026) GSTAformer: graph-guided spatio-temporal autoformer for mid-term wind power forecasting. Energies, 19 (1). 254. ISSN 1996-1073 doi: 10.3390/en19010254

Abstract/Summary

Accurate wind power forecasting is crucial for modern power systems, yet most deep learning models neglect spatial relationships between turbines. We propose GSTAformer, a graph-guided spatio-temporal model capturing both spatial and temporal dependencies through MIC- and PCC-built graphs; GraphSAGE for spatial feature extraction; multi-scale convolution for trend detection; and an improved Autoformer for temporal modeling. Experiments on SDWPF and GEFCom2012 datasets demonstrate GSTAformer’s superior performance, achieving a 24 h mean squared error (MSE) of 0.7480 and mean absolute error (MAE) of 0.6362 on SDWPF. This work integrates graph-based spatial modeling with enhanced temporal forecasting for medium-term wind power prediction, providing a coherent framework suited to complex wind energy scenarios.

Item Type	Article
URI	https://centaur.reading.ac.uk/id/eprint/127890
Identification Number/DOI	10.3390/en19010254
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
Publisher	MDPI Publishing, Basel
Download/View statistics	View download statistics for this item