The Best of Two Worlds: Physics-Informed Neural Networks for Solar Energy Modeling
Solar · 11.11.2026 · 6 (6) · 83
DOI: 10.3390/solar6060083 ↗Kurz gefasst
Fachartikel in der Zeitschrift Solar, online erschienen am 11.11.2026. Verfasst von Marcus Reitz und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.
Abstract (Originalsprache)
The growing worldwide penetration of solar energy into power grids has increased the need for accurate forecasting to reduce supply–demand imbalances and grid congestion. Physics-based models perform well for average conditions. However, edge cases such as very low or high irradiance are challenging for traditional physics-based models, which often underperform under these conditions. Data-driven models offer improved performance in these conditions but typically lack interpretability and insight into the underlying physical mechanisms. To address these limitations, this article presents a combined modeling framework that integrates physics-based principles with machine learning inspired by Physics-Informed Neural Networks (PINNs). The main novelty of this work is a machine learning architecture for solar energy power prediction that explicitly isolates angle of incidence losses and temperature losses in the form of the respective parameters entering a PV power equation as a strict output constraint, which improves interpretability and generalizability, while maintaining high forecasting precision. The methodology is demonstrated using only commonly available commercial system data and validated on both a small-scale research system and a commercial floating solar installation. The results demonstrate significantly improved accuracy over basic physics-based models (0.018 and 0.018 versus 0.023 and 0.029 normalized mean absolute error), particularly for non-standard conditions, and isolate key loss mechanisms.
Förderung
- European Union
Zitieren
APA
Reitz, M., Baig, M. K., & Jong, M. D. (2026). The Best of Two Worlds: Physics-Informed Neural Networks for Solar Energy Modeling. Solar, 6(6), 83. https://doi.org/10.3390/solar6060083
Vancouver
Reitz M, Baig MK, Jong MD. The Best of Two Worlds: Physics-Informed Neural Networks for Solar Energy Modeling. Solar. 2026;6(6):83. doi:10.3390/solar6060083
BibTeX
@article{Reitz2026,
author = {Reitz, Marcus and Baig, Mirza Khalid and Jong, Minne de},
title = {The Best of Two Worlds: Physics-Informed Neural Networks for Solar Energy Modeling},
journal = {Solar},
year = {2026},
volume = {6},
number = {6},
pages = {83},
doi = {10.3390/solar6060083}
}
EUVIMED