Inverted Transformers for Effective Post-Calibration in Multisite Wind Power Forecasting

TY - JOUR

T1 - Inverted Transformers for Effective Post-Calibration in Multisite Wind Power Forecasting

AU - Cohen, Joseph

AU - Xu, Tianyi

AU - Jang, Youngchan

AU - Du, Pengwei

AU - Byon, Eunshin

AU - Huan, Xun

N1 - Publisher Copyright: © 2025 The Author(s). Wind Energy published by John Wiley & Sons Ltd.

PY - 2025/10

Y1 - 2025/10

N2 - Accurate wind power forecasts are essential for energy management and resource allocation. However, because of complex weather dynamics and other nonlinearities, it is exceedingly difficult to forecast wind power on the multisite level for dozens of wind farms at once. This paper proposes a hybridized approach that leverages deep learning to predict future forecast errors from physics-based numerical weather prediction (NWP) model estimates. Utilizing errors from NWP forecasts allows integration of critical atmospheric and meteorological dynamics into the forecasting model, and we demonstrate the importance of post-calibration based on the physics versus pure data-driven wind power prediction. This post-calibration approach is enabled by the inverted transformer architecture, which efficiently and effectively learns meaningful wind farm variate representations, resulting in accurate spatiotemporal corrections to the forecasts. We also investigate modifying the iTransformer with a new embedding approach, named SpaceEmbed, that explicitly encodes spatial distance information into the network. The proposed approach is validated with a case study using real-world data and forecasts from the Electric Reliability Council of Texas (ERCOT) in 2015 for 74 wind farms in Texas at different time scales. Using the high sustained limit as the metric for power generation, the iTransformer outperforms other state-of-the-art deep learning forecasting methods, succeeding at the post-calibration task by reducing NWP forecast error by up to 33% on average.

AB - Accurate wind power forecasts are essential for energy management and resource allocation. However, because of complex weather dynamics and other nonlinearities, it is exceedingly difficult to forecast wind power on the multisite level for dozens of wind farms at once. This paper proposes a hybridized approach that leverages deep learning to predict future forecast errors from physics-based numerical weather prediction (NWP) model estimates. Utilizing errors from NWP forecasts allows integration of critical atmospheric and meteorological dynamics into the forecasting model, and we demonstrate the importance of post-calibration based on the physics versus pure data-driven wind power prediction. This post-calibration approach is enabled by the inverted transformer architecture, which efficiently and effectively learns meaningful wind farm variate representations, resulting in accurate spatiotemporal corrections to the forecasts. We also investigate modifying the iTransformer with a new embedding approach, named SpaceEmbed, that explicitly encodes spatial distance information into the network. The proposed approach is validated with a case study using real-world data and forecasts from the Electric Reliability Council of Texas (ERCOT) in 2015 for 74 wind farms in Texas at different time scales. Using the high sustained limit as the metric for power generation, the iTransformer outperforms other state-of-the-art deep learning forecasting methods, succeeding at the post-calibration task by reducing NWP forecast error by up to 33% on average.

KW - deep learning

KW - time series forecasting

KW - wind power prediction

UR - https://www.scopus.com/pages/publications/105014799981

UR - https://www.scopus.com/pages/publications/105014799981#tab=citedBy

U2 - 10.1002/we.70057

DO - 10.1002/we.70057

M3 - Article

SN - 1095-4244

VL - 28

JO - Wind Energy

JF - Wind Energy

IS - 10

M1 - e70057

ER -