Szczegóły publikacji
Opis bibliograficzny
Unified data-driven prediction of photovoltaics output from weather and geographic data across diverse systems / Joanna Wójcicka, Tomasz HACHAJ // W: FedCSIS [Dokument elektroniczny] : proceedings of the 20th conference on Computer Science and Intelligence Systems : September 14–17, 2025, Kraków, Poland / eds. Marek Bolanowski, [et al.]. — Wersja do Windows. — Dane tekstowe. — Warsaw : Polskie Towarzystwo Informatyczne ; [Piscataway] : IEEE, cop. 2025. — ( Annals of Computer Science and Information Systems ; ISSN 2300-5963 ; vol. 43 ). — Dod. ISBN: 979-8-3315-1531-7. — ISBN: 978-83-973291-7-1; e-ISBN: 978-83-973291-6-4. — S. 405–410. — Wymagania systemowe: Adobe Reader. — Tryb dostępu: https://annals-csis.org/Volume_43/pliks/volume_43.pdf [2025-11-04]. — Bibliogr. s. 410, Abstr.
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 163991 |
|---|---|
| Data dodania do BaDAP | 2025-12-01 |
| DOI | 10.15439/2025F9025 |
| Rok publikacji | 2025 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | Conference on Computer Science and Intelligence Systems 2025 |
| Czasopismo/seria | Annals of Computer Science and Information Systems |
Abstract
As the adoption of renewable energy continues to rise, precise forecasting of solar power generation is essential for optimizing energy storage and distribution. This article explores the prediction of energy output in photovoltaic systems using machine learning models that leverage environmental and geographical factors. The study utilizes data from 9,182 private photovoltaic installations across Poland and publicly available weather records. Additionally, a data preprocessing method was introduced to filter out non-useful data, such as records indicating malfunctioning installations, ensuring that only relevant information is used for prediction. Key variables considered include temperature, cloud cover, wind speed, and solar panel efficiency. This paper studies the effectiveness of data-driven energy production forecasting methods, namely linear regression, polynomial regression, decision tree regression, random forest regression, and multilayer fully connected artificial neural network, designed to make predictions for various installations with different parameters and geographical locations, considering atmospheric conditions in contrast to frequently published articles in which predictions are fitted on data from a single photovoltaic installation. Due to this, our work has broad research value, explores the boundaries and limitations of such approaches, and can be considered a reference for energy engineers, computer scientists, and researchers.
