Photovoltaic power forecasting: A Transformer based framework

The accurate prediction of photovoltaic (PV) energy production is a crucial task to optimise the integration of solar energy into the power grid and maximise the benefit of renewable source trading in the energy market. This paper systematically and quantitatively analyses the literature by comparin...

Full description

Saved in:
Bibliographic Details
Main Authors: Gabriele Piantadosi, Sofia Dutto, Antonio Galli, Saverio De Vito, Carlo Sansone, Girolamo Di Francia
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Energy and AI
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666546824001101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850114213403426816
author Gabriele Piantadosi
Sofia Dutto
Antonio Galli
Saverio De Vito
Carlo Sansone
Girolamo Di Francia
author_facet Gabriele Piantadosi
Sofia Dutto
Antonio Galli
Saverio De Vito
Carlo Sansone
Girolamo Di Francia
author_sort Gabriele Piantadosi
collection DOAJ
description The accurate prediction of photovoltaic (PV) energy production is a crucial task to optimise the integration of solar energy into the power grid and maximise the benefit of renewable source trading in the energy market. This paper systematically and quantitatively analyses the literature by comparing different machine learning techniques and the impact of different meteorological forecast providers. The methodology consists of an irradiance model coupled with a meteorological provider; this combination removes the constraint of a local irradiance measurement. The result is a Transformer Neural Network architecture, trained and tested using OpenMeteo data, whose performance is superior to other combinations, providing a MAE of 1.22 kW (0.95%), and a MAPE of 2.21%. The implications of our study suggest that adopting a comprehensive approach, integrating local weather data, modelled irradiance, and PV plant configuration data, can significantly improve the accuracy of PV power forecasting, thus contributing to more effective technological and economic integration.
format Article
id doaj-art-4b4d4a69c0074c1eaa403259211a40cc
institution OA Journals
issn 2666-5468
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Energy and AI
spelling doaj-art-4b4d4a69c0074c1eaa403259211a40cc2025-08-20T02:36:58ZengElsevierEnergy and AI2666-54682024-12-011810044410.1016/j.egyai.2024.100444Photovoltaic power forecasting: A Transformer based frameworkGabriele Piantadosi0Sofia Dutto1Antonio Galli2Saverio De Vito3Carlo Sansone4Girolamo Di Francia5ENEA CR-Portici, Energy Technologies and Renewable Sources Department, Portici, 80055, ItalyUniversity of Naples Federico II, Electrical Engineering and Information Technology Department, Napoli, 80125, ItalyUniversity of Naples Federico II, Electrical Engineering and Information Technology Department, Napoli, 80125, Italy; Corresponding author.ENEA CR-Portici, Energy Technologies and Renewable Sources Department, Portici, 80055, ItalyUniversity of Naples Federico II, Electrical Engineering and Information Technology Department, Napoli, 80125, ItalyENEA CR-Portici, Energy Technologies and Renewable Sources Department, Portici, 80055, ItalyThe accurate prediction of photovoltaic (PV) energy production is a crucial task to optimise the integration of solar energy into the power grid and maximise the benefit of renewable source trading in the energy market. This paper systematically and quantitatively analyses the literature by comparing different machine learning techniques and the impact of different meteorological forecast providers. The methodology consists of an irradiance model coupled with a meteorological provider; this combination removes the constraint of a local irradiance measurement. The result is a Transformer Neural Network architecture, trained and tested using OpenMeteo data, whose performance is superior to other combinations, providing a MAE of 1.22 kW (0.95%), and a MAPE of 2.21%. The implications of our study suggest that adopting a comprehensive approach, integrating local weather data, modelled irradiance, and PV plant configuration data, can significantly improve the accuracy of PV power forecasting, thus contributing to more effective technological and economic integration.http://www.sciencedirect.com/science/article/pii/S2666546824001101PhotovoltaicForecastingDeep learningTransformers
spellingShingle Gabriele Piantadosi
Sofia Dutto
Antonio Galli
Saverio De Vito
Carlo Sansone
Girolamo Di Francia
Photovoltaic power forecasting: A Transformer based framework
Energy and AI
Photovoltaic
Forecasting
Deep learning
Transformers
title Photovoltaic power forecasting: A Transformer based framework
title_full Photovoltaic power forecasting: A Transformer based framework
title_fullStr Photovoltaic power forecasting: A Transformer based framework
title_full_unstemmed Photovoltaic power forecasting: A Transformer based framework
title_short Photovoltaic power forecasting: A Transformer based framework
title_sort photovoltaic power forecasting a transformer based framework
topic Photovoltaic
Forecasting
Deep learning
Transformers
url http://www.sciencedirect.com/science/article/pii/S2666546824001101
work_keys_str_mv AT gabrielepiantadosi photovoltaicpowerforecastingatransformerbasedframework
AT sofiadutto photovoltaicpowerforecastingatransformerbasedframework
AT antoniogalli photovoltaicpowerforecastingatransformerbasedframework
AT saveriodevito photovoltaicpowerforecastingatransformerbasedframework
AT carlosansone photovoltaicpowerforecastingatransformerbasedframework
AT girolamodifrancia photovoltaicpowerforecastingatransformerbasedframework