Prediction du rayonnement solaire horaire En utilisant les reseaux de neurone artificiel

D. Benatiallah, A. Benatiallah, K. Bouchouicha, B. Nasri

Abstract


Abstract: Measurements of solar radiation are rare and limited to only a few areas across the Algerian territory, the sizing and optimization of solar energy projects is a fundamental and indispensable need, it requires knowing solar radiation data at a geographic location by using efficient models to estimate them. The present work aims to predict and develop a neural model for estimating global hourly solar irradiation, according to some parameters of solar geometry and astronomical data for the Adrar region. To do this, we used nine models and three activation functions. The data is collected by Adrar's Saharan Renewable Energy Research Unit and the SODA database over a six-year period (2013 - 2018), 80% of the data was used to train the neural network and the rest for validation. We have tried several combinations of the input data, which gives different level of precision and it has been concluded that the logistic Sigmoid function of 15 neurons of the hidden layer with correlation coefficient between the measured and estimated global solar irradiation is 98.25 %, may be preferred to estimate global solar radiation intensities for the study site and for other locations with similar climatic conditions.

Résumé : Les mesures du rayonnement  solaire sont rare et  limitées à quelques zones seulement à travers le territoire Algérien,  le dimensionnement et l’optimisation des projets de  l'énergie solaire est un besoin fondamental et indispensable, il nécessite  la connaître des donnés de radiations solaires à une localité géographique d’implantation en utilisant  des modèles efficaces pour les estimer. Le présent travail vise à prédire et développer un modèle neuronal pour estimé l’irradiation  solaire globale horaire, en fonction de quelques paramètres de la géométrie solaire et les données astronomique pour la région d’Adrar. Pour ce faire, nous avons utilisé neuf modèles et trois fonctions d’activation. Les données sont collectées par l’Unité de Recherche en Energies Renouvelables en Milieu Saharien d’Adrar et la base de données SODA sur une période de six ans (2013 - 2018) ces données ont traité et contrôlé,  80% des  données ont été utilisées pour entraîner le réseau et le reste pour la validation. Nous avons essayé plusieurs combinaisons des données d’entrée, qui donne différent niveau de précision et il a été conclu que la fonction Sigmoïde logistique de 15 neurones de la couche cachée, avec coefficient de corrélation entre l’irradiation solaire globale mesuré et estimée est de 98.25%, peut être préférée pour estimer intensités de rayonnement solaire global pour le site étudié et pour d'autres endroits ayant des conditions climatiques similaires.

Full Text:

PDF

References


Sawin, J. Global Status Report. Renewables. REN21 Secretariat, (2013).

Shukla, K.; Sudhakar, K.; Rangneker, S. Estimation and Validation of Solar Radiation Incident on Horizontal and Tilted Surface at Bhopal. Madhya Pradesh India. American-Eurasian Journal of Agriculture & Environnement Sciences 15 (2015) 129-139.

Benatiallah, D.; Benatiallah, A.; Bouchouicha, K. Development and Modeling of a Geographic Information System solar flux in Adrar, Algeria. International Journal of System Modeling and Simulation 1 (2016) 15-19.

Benatiallah, D.;Benatiallah, A.; Bouchouicha, K. Model for obtaining the daily direct and diffuse solar radiations. International Journal of Science and Applied Information Technology 7 (2017) 50-55.

Kambezidis, H.D.; Psiloglou, B.E.; Karagiannis, D.; Dumka, U.C.; Kaskaoutis, D.G. Recent improvements of the Meteorological Radiation Model for solar irradiance estimates under all-sky conditions. Renewable Energy (2016).

Bouchouicha, K.; Bailek, N.; El-Shimy, M. Estimation of Monthly Average Daily Global Solar Radiation Using Meteorological-Based Models in Adrar, Algeria. Applied Solar Energy 6 (2018) 448–455.

Abdo, T.; El-Shimy, M. Estimating the global solar radiation for solar energy projects-Egypt case study. International Journal Sustainable Energy 32 (2013) 682–712.

Mesri, M. Numerical methods to calculate solar radiation, validation through a new Graphic User Interface design. Energy Conversion and Management 90 (2015) 436–445.

Almorox, J.; Benito, M.; Hontoria, C. Estimation of monthly Angström-Prescott equation coefficients from measured daily data in Toledo, Spain. Renewable Energy 30 (2005) 931–936.

Zaatri, A.; Azzizi, N. Evaluation of some mathematical models of solar radiation received by a ground collector. World Journal of Engineering 13 (2016) 376 – 380.

Bakirci, K. Correlations for estimation of daily global solar radiation with hours of bright sunshine in Turkey. Energy 34 (2009) 485–501.

Lealea, T.; Tchinda, R. Estimation of diffuse solar radiation in the north and far north of Cameroon. European Scientific Journal 9 (2013).

Namrata, K.; Sharma, S.; Seksena, S. Empirical models for the estimation of global solar radiation with sunshine hours on horizontal surface for Jharkhand (India). Applied Solar Energy 52 (2011) 164–172.

Mesri-Merad, M.; Rougab, I.; Cheknane, A.; Bachari, N. Estimation du rayonnement solaire au sol par des modèles semi-empiriques, Revue des Energies Renouvelables 15 (2012) 451– 463.

Benatiallah, D.; Benatiallah, A.; Bouchouicha, K.; Nasri B.; Basharat J. A statistical comparative study of clear sky global solar irradiance models under south Algerian climate .Cinecia e Técnica Vitvincola 34 (2019) 14-29,

Almorox, J.; Bocco, M.; Willington, E. Estimation of daily global solar radiation from measured temperatures at Cañada de Luque, Córdoba, Argentina. Renewable Energy 60 (2013) 382–387.

Scarpa, F.; Bianco, V.; Tagliafico, L. A clear sky physical based solar radiation decomposition model. Thermal Science and Engineering Progressing 6 (2018) 323-329.

Karoro, A.; Ssenyonga, T.; Mubiru, J. Predicting Global Solar Radiation using an Artificial Neural Network Single-Parameter Model. Advances in Artificial Neural Systems 20 (2011).

Benghanem, M. Artificial Intelligence Techniques for Prediction of Solar Radiation Data: A Review. International Journal of Renewable Energy Technology 3 (2012) 189- 219.

Mohandes, M.; Rehman, S.; Halawani, TO. Estimation of global solar radiation using artificial neural networks. Renewable Energy 14 (1998) 179–184.

Behrang, MA.; Assareh, E.; Ghanbarzadeh, A.; Noghrehabadi, AR. The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data. Solar Energy 84 (2010) 1468-1480.

Miloudi, L.; Acheli, D.; Kesraoui, M.; Application of Artificial Neural Networks for Forecasting Photovoltaic System Parameters. Applied Solar Energy 53 (2017) 85–91.

Azadeh, A.; Maghsoudi, A.; Sohrabkhani, S. An integrated artificial neural networks approach for predicting global radiation. Energy Conversion and Management (2010).

Mellit, M.; Pavan, A. A 24-h Forecast of Solar Irradiance Using Artificial Neural Network: Application for Performance Prediction of a Grid-Connected PV Plant at Trieste, Italy. Solar Energy 84 (2010) 807–821.

Sfetsos, A.; Coonick, AH. Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques. Solar Energy 68 (2000) 169- 178.

Mohandes, M.; Balghonaim, A.; Kassas, M.; Rehman, S.; Halawani, TO. Use of radial basis functions for estimating monthly mean daily solar radiation. Solar Energy 68 (2000).

Voyant, C.; Muselli, M. ; Paoli, C. ; Nivet, M.L. Optimization of an Artificial Neural Network Dedicated to the Multivariate Forecasting of Daily Global Radiation. Energy 36 (2010) 348–359.

Rehman, S.; Mohandes, M. Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy 63 (2008) 571–576.

Benatiallah, D.; Benatiallah, a.; Bouchouicha, K.; Hamouda, M.; Nasri, B. An empirical model for estimating solar radiation in the Algerian Sahara. American Institute of Physics (2018); doi: 10.1063/1.5039218.

SODA, Site web: www.soda-pro.com/web-services#meteo-data.

Hopfield, J. Neural networks and physical systems with emergent collective computational abilities, PNAS proceedings of national academy of sciences of USA April 1, 79(1982) 25-54 https://doi.org/10.1073/pnas.79.8.2554

Tymvois, F.S. ; Jacovides, C.P. ; Michaelides, S.C. ; Scouteli, C. Comparative study of Angströms and atificial neural networks metodologies in estimationg global solar radiation. Solar Energy (2005).

Ihya, B.; Mechaqrane, A.; Tadili, R.; Bargach, M.n. Estimation de la fraction diffuse a Fès en utilisant les réseaux de neurones artificiels, Congrès International sur les Energies Renouvelables et l’Efficacité Energétique 20-21 Avril (2011), Fès-Maroc.

Tarahi, F. Prédiction de l’irradiation solaire globale pour la région de Tizi-Ouzou par les réseaux de neurones artificiels, mémoire présenté pour l’obtention du diplôme de magister en université Mouloud Mammeri- Tizi-Ouzou, (2011).

Dreyfus, G. ; Martinez, M. ; Samueldies, M. Gordon, M.B ; Badron, F. ; Thiria, S. ; Hérault, L. réseaux de nuerons méthodologie et application. Edition Eyrolles (2002).

Stone, RJ. Improved statistical procedure for the evaluation of solar radiation estimation models. Solar Energy 51 (1993) 289–91.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License. Copyright UMMB © 2020 University M'hamed Bougara - Boumerdes. Independance AV., Boumerdes, 35000 Algeria, Tel/Fax: +213 24 91 14 98/ +213 2491-29-51