EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Out-of-Distribution-Aware Time Series Conformal Prediction with Adaptive Retraining for Solar Power Forecasting

Uroš Ilić, Ognjen Kundačina, Andrija Petrušić, Miona Andrejević Stošović, Novak Radivojević, Zoran Stajić

Energies · 22.07.2026 · 19 (14) · 3446

DOI: 10.3390/en19143446 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 22.07.2026. Verfasst von Uroš Ilić und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science, Technological Development and Innovation of the Republic of Serbia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing integration of photovoltaic systems into modern power grids requires forecasting models that not only provide accurate predictions but also reliable uncertainty quantification under evolving operating conditions. In this paper, we propose an Out-of-distribution-aware time series conformal prediction framework with adaptive retraining, designed to address key limitations of standard conformal prediction methods in temporally dependent and dynamically changing environments. The framework is built upon the Ensemble batch prediction intervals method, which enables distribution-free uncertainty quantification without relying on a fixed calibration set, making it particularly suitable for time series applications. To ensure robustness to distribution shifts, a conformal out-of-distribution detection module is incorporated, where out-of-distribution detection is formulated as a hypothesis testing problem and enhanced through calibration-conditional p-values obtained via the Simes correction, providing conservative false-positive control intended to limit unnecessary model retraining. The proposed framework demonstrates superior performance compared to state-of-the-art approaches in uncertainty quantification, while conformal out-of-distribution detection reduces false positives and the adaptive retraining mechanism ensures effective adaptation to evolving data distributions in real-world scenarios.

Förderung

  • Ministry of Science, Technological Development and Innovation of the Republic of Serbia

Zitieren

APA

Ilić, U., Kundačina, O., Petrušić, A., Stošović, M. A., Radivojević, N., & Stajić, Z. (2026). Out-of-Distribution-Aware Time Series Conformal Prediction with Adaptive Retraining for Solar Power Forecasting. Energies, 19(14), 3446. https://doi.org/10.3390/en19143446

Vancouver

Ilić U, Kundačina O, Petrušić A, Stošović MA, Radivojević N, Stajić Z. Out-of-Distribution-Aware Time Series Conformal Prediction with Adaptive Retraining for Solar Power Forecasting. Energies. 2026;19(14):3446. doi:10.3390/en19143446

BibTeX
@article{Ili2026,
  author = {Ilić, Uroš and Kundačina, Ognjen and Petrušić, Andrija and Stošović, Miona Andrejević and Radivojević, Novak and Stajić, Zoran},
  title = {Out-of-Distribution-Aware Time Series Conformal Prediction with Adaptive Retraining for Solar Power Forecasting},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {14},
  pages = {3446},
  doi = {10.3390/en19143446}
}
Kostenlos starten →