Efficient Machine Learning-Based Prediction of Solar Irradiance Using Multi-Site Data

Hassan N. Noura (), Zaid Allal, Ola Salman and Khaled Chahine
Additional contact information
Hassan N. Noura: Institut FEMTO-ST, CNRS, IUT-NFC, Université Marie et Louis Pasteur, F-90000 Belfort, France
Zaid Allal: LISTIC, Polytech Annecy-Chambéry, Université Savoie Mont Blanc, 74944 Annecy Cedex, France
Ola Salman: DeepVu, Berkeley, CA 94704, USA
Khaled Chahine: College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait

Future Internet, 2025, vol. 17, issue 8, 1-37

Abstract: Photovoltaic panels have become a promising solution for generating renewable energy and reducing our reliance on fossil fuels by capturing solar energy and converting it into electricity. The effectiveness of this conversion depends on several factors, such as the quality of the solar panels and the amount of solar radiation received in a specific region. This makes accurate solar irradiance forecasting essential for planning and managing efficient solar power systems. This study examines the application of machine learning (ML) models for accurately predicting global horizontal irradiance (GHI) using a three-year dataset from six distinct photovoltaic stations: NELHA, ULL, HSU, RaZON+, UNLV, and NWTC. The primary aim is to identify optimal shared features for GHI prediction across multiple sites using a 30 min time shift based on autocorrelation analysis. Key features identified for accurate GHI prediction include direct normal irradiance (DNI), diffuse horizontal irradiance (DHI), and solar panel temperatures. The predictions were performed using tree-based algorithms and ensemble learners, achieving R 2 values exceeding 95% at most stations, with NWTC reaching 99%. Gradient Boosting Regression (GBR) performed best at NELHA, NWTC, and RaZON, while Multi-Layer Perceptron (MLP) excelled at ULL and UNLV. CatBoost was optimal for HSU. The impact of time-shifting values on performance was also examined, revealing that larger shifts led to performance deterioration, though MLP performed well under these conditions. The study further proposes a stacking ensemble approach to enhance model generalizability, integrating the strengths of various models for more robust GHI prediction.

Keywords: global horizontal irradiance; solar energy; machine learning; explainable AI (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/17/8/336/pdf (application/pdf)
https://www.mdpi.com/1999-5903/17/8/336/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:17:y:2025:i:8:p:336-:d:1711094

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().