Hybrid Models for Daily Global Solar Radiation Assessment

Daily solar radiation forecasting has recently become critical in developing solar energy and its integration into grid systems. Despite the huge number of proposed forecasting techniques, an accurate estimation remains a significant challenge because of the non-stationary variation of solar radiat...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdelkerim Souahlia, Abdelhalim Rabehi, Abdelazize Rabehi
Format: Article
Language:English
Published: Universidade Federal de Viçosa (UFV) 2023-06-01
Series:The Journal of Engineering and Exact Sciences
Subjects:
Online Access:https://periodicos.ufv.br/jcec/article/view/15926
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832569711000289280
author Abdelkerim Souahlia
Abdelhalim Rabehi
Abdelazize Rabehi
author_facet Abdelkerim Souahlia
Abdelhalim Rabehi
Abdelazize Rabehi
author_sort Abdelkerim Souahlia
collection DOAJ
description Daily solar radiation forecasting has recently become critical in developing solar energy and its integration into grid systems. Despite the huge number of proposed forecasting techniques, an accurate estimation remains a significant challenge because of the non-stationary variation of solar radiation components due to the continuously changing climatic conditions. Usually, several input data predictors are used for the forecasting process, which can cause redundancy and correlation between data features. This work assesses a set of feature selection techniques to check their ability to select the relevant predictors and reduce redundant and irrelevant information. An Artificial Neural Network is used to fit the measured solar radiation based on the selected features. The developed model is evaluated through various objective evaluation metrics using historical data of three years measured at the Ghardaiaregion inAlgeria. Results show the effectiveness of the proposed method, where values of 0,0189, 0.0286, 5.4387, and 98.28% have been found as MABE, RMSE, nRMSE and r, respectively.
format Article
id doaj-art-20f1e55d539f4762bf353efeba942d46
institution Kabale University
issn 2527-1075
language English
publishDate 2023-06-01
publisher Universidade Federal de Viçosa (UFV)
record_format Article
series The Journal of Engineering and Exact Sciences
spelling doaj-art-20f1e55d539f4762bf353efeba942d462025-02-02T19:55:07ZengUniversidade Federal de Viçosa (UFV)The Journal of Engineering and Exact Sciences2527-10752023-06-019410.18540/jcecvl9iss4pp15926-01eHybrid Models for Daily Global Solar Radiation Assessment Abdelkerim Souahlia0Abdelhalim Rabehi1Abdelazize Rabehi2Telecommunications and smart systems Laboratory, University of ZianeAchour, Djelfa 17000, Algeria.Telecommunications and smart systems Laboratory, University of ZianeAchour, Djelfa 17000, Algeria.Telecommunications and smart systems Laboratory, University of ZianeAchour, Djelfa 17000, Algeria. Daily solar radiation forecasting has recently become critical in developing solar energy and its integration into grid systems. Despite the huge number of proposed forecasting techniques, an accurate estimation remains a significant challenge because of the non-stationary variation of solar radiation components due to the continuously changing climatic conditions. Usually, several input data predictors are used for the forecasting process, which can cause redundancy and correlation between data features. This work assesses a set of feature selection techniques to check their ability to select the relevant predictors and reduce redundant and irrelevant information. An Artificial Neural Network is used to fit the measured solar radiation based on the selected features. The developed model is evaluated through various objective evaluation metrics using historical data of three years measured at the Ghardaiaregion inAlgeria. Results show the effectiveness of the proposed method, where values of 0,0189, 0.0286, 5.4387, and 98.28% have been found as MABE, RMSE, nRMSE and r, respectively. https://periodicos.ufv.br/jcec/article/view/15926Solar radiation, renewable energy, features selection, Forecasting, Artificial Neural Networks.
spellingShingle Abdelkerim Souahlia
Abdelhalim Rabehi
Abdelazize Rabehi
Hybrid Models for Daily Global Solar Radiation Assessment
The Journal of Engineering and Exact Sciences
Solar radiation, renewable energy, features selection, Forecasting, Artificial Neural Networks.
title Hybrid Models for Daily Global Solar Radiation Assessment
title_full Hybrid Models for Daily Global Solar Radiation Assessment
title_fullStr Hybrid Models for Daily Global Solar Radiation Assessment
title_full_unstemmed Hybrid Models for Daily Global Solar Radiation Assessment
title_short Hybrid Models for Daily Global Solar Radiation Assessment
title_sort hybrid models for daily global solar radiation assessment
topic Solar radiation, renewable energy, features selection, Forecasting, Artificial Neural Networks.
url https://periodicos.ufv.br/jcec/article/view/15926
work_keys_str_mv AT abdelkerimsouahlia hybridmodelsfordailyglobalsolarradiationassessment
AT abdelhalimrabehi hybridmodelsfordailyglobalsolarradiationassessment
AT abdelazizerabehi hybridmodelsfordailyglobalsolarradiationassessment