EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Resolution Day-Ahead PV Power Forecasting with Wavelet–CNN–LSTM and Calibrated Uncertainty: A Rabigh PVGIS Case Study

Faisal Albeladi, Mohamed E. Dessouki, Malek Alduhaymi, Kamal Basulaiman, Abdulrahman Almazroui, Faisal Alhassani

Energies · 07.11.2026 · 19 (21) · 5345

DOI: 10.3390/en19215345 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 07.11.2026. Verfasst von Faisal Albeladi und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Abdulaziz University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Day-ahead photovoltaic (PV) forecasting must resolve the coexistence of a smooth diurnal generation envelope and shorter-scale fluctuations while providing uncertainty information suitable for operational decision making. This paper develops a multi-resolution Wavelet–CNN–LSTM framework for 24 h ahead PV power forecasting and evaluates it using a five-year PVGIS-derived dataset for a 334.116 MW Rabigh case study. The forecasting information set is restricted to the preceding 24 h of PV power and meteorological observations, together with deterministic target-day temporal variables. A validation study selects a Haar level-2 decomposition of PV history into A2, D2, and D1 components, which are processed through parallel convolutional branches before recurrent fusion. The resulting network contains 87,032 trainable parameters. On the 2023 temporal evaluation period, the proposed model achieves an RMSE of 17.228 MW, R2=0.9641, and a daylight RMSE of 24.636 MW, corresponding to 25.69% forecast skill relative to 24 h seasonal persistence. A 7-day moving-block bootstrap confirms clear RMSE reductions relative to persistence and XGBoost, while the intervals for LSTM and CNN–LSTM include zero, indicating statistically comparable performance among the strongest recurrent models. Probabilistic forecasts obtained from 100-pass Monte Carlo dropout yield daylight PICP = 0.9279, MPIW = 84.06 MW, and Winkler score = 122.08 for nominal 90% intervals; an independent conformal calibration set requires no additional widening of the neural interval. The results show that multi-resolution representation can improve squared-error performance without sacrificing model compactness, while calibrated uncertainty provides a complementary measure of forecast reliability.

Förderung

  • King Abdulaziz University

Zitieren

APA

Albeladi, F., Dessouki, M. E., Alduhaymi, M., Basulaiman, K., Almazroui, A., & Alhassani, F. (2026). Multi-Resolution Day-Ahead PV Power Forecasting with Wavelet–CNN–LSTM and Calibrated Uncertainty: A Rabigh PVGIS Case Study. Energies, 19(21), 5345. https://doi.org/10.3390/en19215345

Vancouver

Albeladi F, Dessouki ME, Alduhaymi M, Basulaiman K, Almazroui A, Alhassani F. Multi-Resolution Day-Ahead PV Power Forecasting with Wavelet–CNN–LSTM and Calibrated Uncertainty: A Rabigh PVGIS Case Study. Energies. 2026;19(21):5345. doi:10.3390/en19215345

BibTeX
@article{Albeladi2026,
  author = {Albeladi, Faisal and Dessouki, Mohamed E. and Alduhaymi, Malek and Basulaiman, Kamal and Almazroui, Abdulrahman and Alhassani, Faisal},
  title = {Multi-Resolution Day-Ahead PV Power Forecasting with Wavelet–CNN–LSTM and Calibrated Uncertainty: A Rabigh PVGIS Case Study},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {21},
  pages = {5345},
  doi = {10.3390/en19215345}
}
Kostenlos starten →