Litcius/Paper detail

GSTAformer: Graph-Guided Spatio-Temporal Autoformer for Mid-Term Wind Power Forecasting

Shi Yuan, Yulu Mao, Chenyu Tian, Fei Yu, Tengyue Guo, Min Xia

2026Energies6 citationsDOIOpen Access PDF

Abstract

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.

Topics & Concepts

Wind powerConvolution (computer science)Mean squared errorComputer scienceWind power forecastingWind speedMeteorologyWork (physics)Feature (linguistics)Power (physics)Energy (signal processing)Data modelingEnvironmental scienceTemporal scalesDeep learningSpatial ecologyArtificial intelligenceTemporal resolutionData miningSpatial variabilityElectric power systemApproximation errorMean squared prediction errorProbabilistic forecastingMean absolute percentage errorField (mathematics)Mean absolute errorMode (computer interface)Energy Load and Power ForecastingSolar Radiation and PhotovoltaicsTime Series Analysis and Forecasting
GSTAformer: Graph-Guided Spatio-Temporal Autoformer for Mid-Term Wind Power Forecasting | Litcius