AI-Enhanced Photovoltaic Power Prediction Under Cross-Continental Dust Events and Air Composition Variability in the Mediterranean Region
Energies · 15.07.2025 · 18 (14) · 3731
DOI: 10.3390/en18143731 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 15.07.2025. Verfasst von Pavlos Nikolaidis. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate short-term forecasting of photovoltaic power generation is vital for the operational stability of isolated energy systems, especially in regions with increasing renewable energy penetration. This study presents a novel AI-based forecasting framework applied to the island of Cyprus. Using machine learning methods, particularly regression trees, the proposed approach evaluates the impact of key environmental variables on PV performance, with an emphasis on atmospheric dust transport and air composition variability. A distinguishing feature of this work is the integration of cross-continental dust events and diverse atmospheric parameters into a structured forecasting model. A new clustering methodology is introduced to classify these inputs and analyze their correlation with PV output, enabling improved feature selection for model training. Importantly, all input parameters are sourced from publicly accessible, internet-based platforms, facilitating wide reproducibility and operational application. The obtained results demonstrate that incorporating dust deposition and air composition features significantly enhances forecasting accuracy, particularly during severe dust episodes. This research not only fills a notable gap in the PV forecasting literature but also provides a scalable model for other dust-prone regions transitioning to high levels of solar energy integration.
Zitieren
APA
Nikolaidis, P. (2025). AI-Enhanced Photovoltaic Power Prediction Under Cross-Continental Dust Events and Air Composition Variability in the Mediterranean Region. Energies, 18(14), 3731. https://doi.org/10.3390/en18143731
Vancouver
Nikolaidis P. AI-Enhanced Photovoltaic Power Prediction Under Cross-Continental Dust Events and Air Composition Variability in the Mediterranean Region. Energies. 2025;18(14):3731. doi:10.3390/en18143731
BibTeX
@article{Nikolaidis2025,
author = {Nikolaidis, Pavlos},
title = {AI-Enhanced Photovoltaic Power Prediction Under Cross-Continental Dust Events and Air Composition Variability in the Mediterranean Region},
journal = {Energies},
year = {2025},
volume = {18},
number = {14},
pages = {3731},
doi = {10.3390/en18143731}
}
EUVIMED