Comparison of Machine Learning Techniques to Forecast the Output Power of Photovoltaic Panels using Multiple Prediction Factors

Souhaila Chahboun, Mohamed Maaroufi

2021

Abstract

When the energy transition is unavoidable and artificial intelligence is omnipresent, renewable energies production prediction is becoming a popular concept, especially with the availability of big data sets and the crucial need to forecast these energies known to have a random nature. Thus, the critical goal of this paper is to compare the performance of two approaches, including traditional linear regression and non-linear regression analysis, for the forecasting of the power trends of photovoltaic panels, and thus determine the model giving the most reliable predictions. This study revealed that the non-linear approach provides the best prediction result since it achieved an R²=94% in the testing phase, and its root mean square error is the lowest value RMSE=0.51 Kw.

Paper Citation

in Harvard Style

Chahboun S. and Maaroufi M. (2021). Comparison of Machine Learning Techniques to Forecast the Output Power of Photovoltaic Panels using Multiple Prediction Factors. In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML, ISBN 978-989-758-559-3, pages 474-478. DOI: 10.5220/0010736800003101

in Bibtex Style

@conference{bml21,
author={Souhaila Chahboun and Mohamed Maaroufi},
title={Comparison of Machine Learning Techniques to Forecast the Output Power of Photovoltaic Panels using Multiple Prediction Factors},
booktitle={Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,},
year={2021},
pages={474-478},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010736800003101},
isbn={978-989-758-559-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,
TI - Comparison of Machine Learning Techniques to Forecast the Output Power of Photovoltaic Panels using Multiple Prediction Factors
SN - 978-989-758-559-3
AU - Chahboun S.
AU - Maaroufi M.
PY - 2021
SP - 474
EP - 478
DO - 10.5220/0010736800003101