Journal Home > Volume 5 , Issue 4
Big Data Mining and Analytics 2022, 5(4): 309-317 https://doi.org/10.26599/BDMA.2022.9020003
Open Access | Issue | Published: 18 July 2022

Effect of Feature Selection on the Prediction of Direct Normal Irradiance

Show Author's Information Mohamed Khalifa Boutahir( ),  Yousef Farhaoui,  Mourade Azrour,  Imad Zeroual,  Ahmad El Allaoui
Faculty of Sciences and Techniques, Moulay Ismail University, Errachidia 52000, Morocco
Keywords:
deep learning, machine learning, solar radiation, renewable energies, feature importance
Cite this article:
Boutahir MK, Farhaoui Y, Azrour M, et al. Effect of Feature Selection on the Prediction of Direct Normal Irradiance. Big Data Mining and Analytics, 2022, 5(4): 309-317. https://doi.org/10.26599/BDMA.2022.9020003
Download citation
EndNote(RIS)
BibTeX

890

Views

96

Downloads

Citations

16

Crossref

2

WoS

13

Scopus

0

CSCD

Abstract Full text About this article

Solar radiation is capable of producing heat, causing chemical reactions, or generating electricity. Thus, the amount of solar radiation at different times of the day must be determined to design and equip all solar systems. Moreover, it is necessary to have a thorough understanding of different solar radiation components, such as Direct Normal Irradiance (DNI), Diffuse Horizontal Irradiance (DHI), and Global Horizontal Irradiance (GHI). Unfortunately, measurements of solar radiation are not easily accessible for the majority of regions on the globe. This paper aims to develop a set of deep learning models through feature importance algorithms to predict the DNI data. The proposed models are based on historical data of meteorological parameters and solar radiation properties in a specific location of the region of Errachidia, Morocco, from January 1, 2017, to December 31, 2019, with an interval of 60 minutes. The findings demonstrated that feature selection approaches play a crucial role in forecasting of solar radiation accurately when compared with the available data.


menu
Abstract
Full text
Outline
About this article

Effect of Feature Selection on the Prediction of Direct Normal Irradiance

Show Author's information Mohamed Khalifa Boutahir( ), Yousef Farhaoui, Mourade Azrour, Imad Zeroual, Ahmad El Allaoui
Faculty of Sciences and Techniques, Moulay Ismail University, Errachidia 52000, Morocco

Abstract

Solar radiation is capable of producing heat, causing chemical reactions, or generating electricity. Thus, the amount of solar radiation at different times of the day must be determined to design and equip all solar systems. Moreover, it is necessary to have a thorough understanding of different solar radiation components, such as Direct Normal Irradiance (DNI), Diffuse Horizontal Irradiance (DHI), and Global Horizontal Irradiance (GHI). Unfortunately, measurements of solar radiation are not easily accessible for the majority of regions on the globe. This paper aims to develop a set of deep learning models through feature importance algorithms to predict the DNI data. The proposed models are based on historical data of meteorological parameters and solar radiation properties in a specific location of the region of Errachidia, Morocco, from January 1, 2017, to December 31, 2019, with an interval of 60 minutes. The findings demonstrated that feature selection approaches play a crucial role in forecasting of solar radiation accurately when compared with the available data.

Keywords: deep learning, machine learning, solar radiation, renewable energies, feature importance

References(30)

[1]
M. Oliver and T. Jackson, Energy and economic evaluation of building-integrated photovoltaics, Energy, vol. 26, no. 4, pp. 431–439, 2001.
DOI Google Scholar
[2]
H. Jiang, N. Lu, J. Qin, W. J. Tang, and L. Yao, A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data, Renew. Sustain. Energy Rev., vol. 114, p. 109327, 2019.
DOI Google Scholar
[3]
L. Chen, G. J. Yan, T. X. Wang, H. Z. Ren, J. Calbó, J. Zhao, and R. Mckenzie, Estimation of surface shortwave radiation components under all sky conditions: Modeling and sensitivity analysis, Remote Sen. Environ., vol. 123, pp. 457–469, 2012.
DOI Google Scholar
[4]
P. D. Fu and P. M. Rich, A geometric solar radiation model with applications in agriculture and forestry, Comput. Electron. Agric., vol. 37, nos. 1–3, pp. 25–35, 2002.
DOI Google Scholar
[5]
K. Kaba, M. Sarıgül, M. Avci, and H. M. Kandırmaz, Estimation of daily global solar radiation using deep learning model, Energy, vol. 162, pp. 126–135, 2018.
DOI Google Scholar
[6]
D. Z. Yang, Validation of the 5-min irradiance from the national solar radiation database (NSRDB), J. Renew. Sustain. Energy, vol. 13, no. 1, p. 016101, 2021.
DOI Google Scholar
[7]
W. Q. Zhang, W. Kleiber, A. R. Florita, B. M. Hodge, and B. Mather, Modeling and simulation of high-frequency solar irradiance, IEEE J. Photovolt., vol. 9, no. 1, pp. 124–131, 2019.
DOI Google Scholar
[8]
C. A. Gueymard, A. Habte, and M. Sengupta, Reducing uncertainties in large-scale solar resource data: The impact of aerosols, IEEE J. Photovolt., vol. 8, no. 6, pp. 1732–1737, 2018.
DOI Google Scholar
[9]
O. N. Mensour, S. Bouaddi, B. Abnay, B. Hlimi, and A. Ihlal, Mapping and estimation of monthly global solar irradiation in different zones in Souss-Massa area, Morocco, using artificial neural networks, Int.J. Photoenergy, vol. 2017, p. 8547437, 2017.
DOI Google Scholar
[10]
B. Benamrou, M. Ouardouz, I. Allaouzi, and M. B. Ahmed, A proposed model to forecast hourly global solar irradiation based on satellite derived data, deep learning and machine learning approaches, J. Ecol. Eng., vol. 21, no. 4, pp. 26–28, 2020.
DOI Google Scholar
[11]
H. Ettayyebi and K. El Himdi, Artificial neural networks for forecasting the 24 hours ahead of global solar irradiance, AIP Conf. Proc., vol. 2056, no. 1, p. 020010, 2018.
DOI Google Scholar
[12]
M. A. Jallal, A. El Yassini, S. Chabaa, A. Zeroual, and S. Ibnyaich, A deep learning algorithm for solar radiation time series forecasting: A case study of El Kelaa des Sraghna city, Rev. d’Intell. Artif., vol. 34, no. 5, pp. 563–569, 2020.
DOI Google Scholar
[13]
W. Bendali, I. Saber, B. Bourachdi, M. Boussetta, and Y. Mourad, Deep learning using genetic algorithm optimization for short term solar irradiance forecasting, in Proc. 4th Int. Conf. on Intelligent Computing in Data Sciences (ICDS), Fez, Morocco, 2020, pp. 1–8.
DOI Google Scholar
[14]
Y. Zhou, Y. F. Liu, D. J. Wang, X. J. Liu, and Y. Y. Wang, A review on global solar radiation prediction with machine learning models in a comprehensive perspective, Energy Convers. Manag., vol. 235, p. 113960, 2021.
DOI Google Scholar
[15]
E. D. Obando, S. X. Carvajal, and J. P. Agudelo, Solar radiation prediction using machine learning techniques: A review, IEEE Latin America Transactions, vol. 17, no. 4, pp. 684–697, 2019.
DOI Google Scholar
[16]
Y. Feng, W. P. Hao, H. R. Li, N. B. Cui, D. Z. Gong, and L. L. Gao, Machine learning models to quantify and map daily global solar radiation and photovoltaic power, Renew. Sustain. Energy Rev., vol. 118, p. 109393, 2020.
DOI Google Scholar
[17]
O. Bamisile, A. Oluwasanmi, C. Ejiyi, N. Yimen, S. Obiora, and Q. Huang, Comparison of machine learning and deep learning algorithms for hourly global/diffuse solar radiation predictions, Int. J. Energy Res., .
DOI Google Scholar
[18]
C. Paoli, C. Voyant, M. Muselli, and M. L. Nivet, Forecasting of preprocessed daily solar radiation time series using neural networks, Sol. Energy, vol. 84, no. 12, pp. 2146–2160, 2010.
DOI Google Scholar
[19]
F. Wang, Z. Zhen, B. Wang, and Z. Q. Mi, Comparative study on KNN and SVM based weather classification models for day ahead short term solar PV power forecasting, Appl. Sci., vol. 8, no. 1, p. 28, 2018.
DOI Google Scholar
[20]
H. Munir and I. Y. Chung, Day-ahead solar irradiance forecasting for microgrids using a long short-term memory recurrent neural network: A deep learning approach, Energies, vol. 12, no. 10, p. 1856, 2019.
DOI Google Scholar
[21]
A. Torres-Barrán, Á. Alonso, and J. R. Dorronsoro, Regression tree ensembles for wind energy and solar radiation prediction, Neurocomputing, vol. 326–327, pp. 151–160, 2019.
DOI Google Scholar
[22]
M. Almaraashi, Investigating the impact of feature selection on the prediction of solar radiation in different locations in Saudi Arabia, Appl. Soft Comput., vol. 66, pp. 250–263, 2018.
DOI Google Scholar
[23]
J. L. Fan, X. K. Wang, F. C. Zhang, X. Ma, and L. F. Wu, Predicting daily diffuse horizontal solar radiation in various climatic regions of China using support vector machine and tree-based soft computing models with local and extrinsic climatic data, J. Clean. Prod., vol. 248, p. 119264, 2020.
DOI Google Scholar
[24]
M. Chaibi, E. M. Benghoulam, L. Tarik, M. Berrada, and A. El Hmaidi, An interpretable machine learning model for daily global solar radiation prediction, Energies, vol. 14, no. 21, p. 7367, 2021.
DOI Google Scholar
[25]
S. Vashishtha, Differentiate between the DNI, DHI and GHI? First Green Consulting, https://cutt.ly/xA8nsUd, 2012.
[26]
K. Brush, Data visualization, tech target search business analytics, https://searchbusinessanalytics.techtarget.com/definition/data-visualization, 2020.
[27]
J. Brownlee, Feature importance and feature selection with XGBoost in python, Machine Learning Mastery, https://machinelearningmastery.com/feature-importance-and-feature-selection-with-xgboost-in-python/, 2016.
[28]
P. Ploński, Random forest feature importance computed in 3 ways with python, MLJAR, https://mljar.com/blog/feature-importance-in-random-forest/, 2020.
[29]
S. Thiesen, CatBoost regression in 6 minutes: A brief hands-on introduction to CatBoost regression analysis in Python, toward data science, https://towardsdatascience.com/catboost-regression-in-6-minutes-3487f3e5b329, 2021.
[30]
Evaluation of Feature Selection Methods, https://simility.com/wp-content/uploads/2020/07/WP-Feature-Selection.pdf, 2020.
Publication history
Copyright
Rights and permissions

Publication history

Received: 31 December 2021
Accepted: 24 January 2022
Published: 18 July 2022
Issue date: December 2022

Copyright

© The author(s) 2022.

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return