EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Physics-Guided Residual Correction Framework for Four-Hour-Ahead Photovoltaic Power Forecasting

Yihang Ou Yang, Yufeng Guo, Dazhi Yang, Junci Tang, Qun Yang, Yuxin Jiang, Lichaozheng Qin, Lai Jiang

Electronics · 27.04.2026 · 15 (9) · 1842

DOI: 10.3390/electronics15091842 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 27.04.2026. Verfasst von Yihang Ou Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Corporation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate ultra-short-term photovoltaic (PV) power forecasting is essential for secure grid dispatch and renewable-rich system operation, yet it remains difficult because of rapid weather fluctuations and error accumulation in multi-step prediction. This paper proposes a decoupled physics-guided residual-correction framework, built on an attention-based sequence-to-sequence (Seq2Seq) architecture, for deterministic 4 h ahead rolling PV forecasting at 15 min resolution. In the first stage, a physical model maps numerical weather prediction (NWP) inputs to a deterministic baseline trajectory while preserving physical bounds. In the second stage, an Attention-Seq2Seq network learns the structured residual trajectory from historical sequences. The global attention mechanism allows the decoder to focus on the most informative historical states, helping reduce information loss and error accumulation over extended horizons. Experiments on a 22-month real-world PV dataset show that the proposed framework outperforms conventional linear and nonlinear benchmarks, reducing root mean square error (RMSE) and mean absolute error (MAE) by 23.79% and 39.17%, respectively, relative to the physical baseline. The framework also maintains robust instantaneous tracking under rapidly changing cloud conditions and preserves a 30–40% error reduction rate at Steps 12–16, supporting reliable intraday scheduling.

Förderung

  • State Grid Corporation of China

Zitieren

APA

Yang, Y. O., Guo, Y., Yang, D., Tang, J., Yang, Q., Jiang, Y., Qin, L., & Jiang, L. (2026). A Physics-Guided Residual Correction Framework for Four-Hour-Ahead Photovoltaic Power Forecasting. Electronics, 15(9), 1842. https://doi.org/10.3390/electronics15091842

Vancouver

Yang YO, Guo Y, Yang D, Tang J, Yang Q, Jiang Y, et al. A Physics-Guided Residual Correction Framework for Four-Hour-Ahead Photovoltaic Power Forecasting. Electronics. 2026;15(9):1842. doi:10.3390/electronics15091842

BibTeX
@article{Yang2026,
  author = {Yang, Yihang Ou and Guo, Yufeng and Yang, Dazhi and Tang, Junci and Yang, Qun and Jiang, Yuxin and Qin, Lichaozheng and Jiang, Lai},
  title = {A Physics-Guided Residual Correction Framework for Four-Hour-Ahead Photovoltaic Power Forecasting},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {9},
  pages = {1842},
  doi = {10.3390/electronics15091842}
}
Kostenlos starten →