Forecasting Solar Energy Production Through Modeling of Photovoltaic System Data for Sustainable Energy Planning
Applied Sciences · 19.05.2026 · 16 (10) · 5053
DOI: 10.3390/app16105053 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.05.2026. Verfasst von Fatima Sapundzhi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.
Abstract (Originalsprache)
This paper investigates solar energy production forecasting at a monthly temporal resolution using a pooled neural network framework applied to the Chikalov photovoltaic systems in southwestern Bulgaria. The study considers several related PV installations with unequal time-series lengths and formulates the forecasting task as one-step-ahead prediction of the next monthly total energy yield, measured in kWh, in a global pooled setting. Two complementary neural architectures are compared: a multilayer perceptron (MLP), which serves as a nonlinear feed-forward benchmark based on lagged observations and seasonal descriptors, and a gated recurrent unit (GRU), which explicitly models sequential temporal dependence. In both cases, seasonality is represented through cyclical calendar encodings, while model selection is performed by chronological hyperparameter search using a separate validation block. Forecast accuracy is assessed by RMSE, MAE, coefficient of determination (R2), MAPE, and sMAPE, and uncertainty is quantified through validation residual prediction intervals. The results show that the MLP achieves stronger validation performance, whereas the GRU provides better final out-of-sample generalization after refitting on the combined training and validation data. For both architectures, the best configurations are obtained with a 12-month input horizon, indicating that one full annual cycle contains the most informative memory for forecasting monthly aggregated photovoltaic energy yield in the considered dataset. After refitting on the combined training and validation data, the GRU achieved the best final out-of-sample performance, with RMSE = 296.38 kWh, MAE = 213.16 kWh, R2 = 0.9231, MAPE = 7.52%, and sMAPE = 7.49%. Overall, the findings demonstrate that pooled neural modeling is an effective framework for monthly PV production forecasting and can provide practically useful support for sustainable energy planning, monitoring, and optimization.
Förderung
- European Union
Zitieren
APA
Sapundzhi, F., Georgiev, S., Georgiev, I., & Todorov, V. (2026). Forecasting Solar Energy Production Through Modeling of Photovoltaic System Data for Sustainable Energy Planning. Applied Sciences, 16(10), 5053. https://doi.org/10.3390/app16105053
Vancouver
Sapundzhi F, Georgiev S, Georgiev I, Todorov V. Forecasting Solar Energy Production Through Modeling of Photovoltaic System Data for Sustainable Energy Planning. Applied Sciences. 2026;16(10):5053. doi:10.3390/app16105053
BibTeX
@article{Sapundzhi2026,
author = {Sapundzhi, Fatima and Georgiev, Slavi and Georgiev, Ivan and Todorov, Venelin},
title = {Forecasting Solar Energy Production Through Modeling of Photovoltaic System Data for Sustainable Energy Planning},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {10},
pages = {5053},
doi = {10.3390/app16105053}
}
EUVIMED