Open Access Open Access  Restricted Access Subscription or Fee Access

Energy Supply Management Using the Solar Energy Prediction in Smart Grid

Abdelilah Kahaji(1*), Rachid Alaoui(2), Sadik Farhat(3), Lahoussine Bouhouch(4)

(1) Faculty of Science, Ibn Zohr University, Morocco
(2) Faculty of Science, Ibn Zohr University, Morocco
(3) Faculty of Science, Ibn Zohr University, Morocco
(4) Faculty of Science, Ibn Zohr University, Morocco
(*) Corresponding author



The most significant challenge in a smart grid (SG) is the control of the function of supply and the demand of electric energy. Indeed, some difficulties arise during the management of the electric energy storage and the intermittency of renewable energy. In particular, these problems are encountered during the preparations of the product promotions and the sales price updates for one to several days (j + n). The prediction of these types of energy is only possible through smart tools and solutions.This paper therefore presents a work proponing the development of an optimized method for a daily solar energy prediction. This modelisbased on the neural network multilayer perceptron model (MLP) and on the preprocessing techniques stationarity of time series (TS) obtained by the Autoregressive moving average method (ARMA). This method consists in making the historical measures of the solar irradiation stationary before implementing the MLP model. The incorporation of this technique has helped to reduce the root Mean Square Error (RMSE) to 0.51 kWh/m2/day, hence obtaininga reduction of 0.11 kWh/m2/day of the RMSE (-16%) compared to the MLP model without preprocessing of the stationarity developed in advance. This optimization has significantly improved the prediction of the daily solar irradiation. It has set the present MLP model among the best predictors studied in the many recent researches in the literature.
Copyright © 2016 Praise Worthy Prize - All rights reserved.


Smart Grid; Prediction; Energy Supply Management; Multilayer Perceptron Model; Renewable Energy; Solar Energy

Full Text:



Web site:

Web site:,13554.html

A. Kahaji, R. Alaoui, S. Farhat, A. Ihlal, L. Bouhouch, Modèle de prédiction des performances énergétiques d'alimentations photovoltaïques des BTS par l'architecture MLP, CMT 2012, Fès-Maroc, Mars 2012, pp. 179-182.

Z.W. Zheng, Y.Y. Chen, M.M. Huo, B. Zhao, An Overview: The Development of Prediction Technology of Wind and Photovoltaic Power Generation, Energy Procedia, Vol. 12, 2011, pp. 601-608.

S. Belaid, A. Mellit, Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate, Energy Conversion and Management, Vol. 118, 2016, pp 105-118.

K. Chiteka, C.C. Enweremadu, Prediction of global horizontal solar irradiance in Zimbabwe using artificial neural networks, Journal of Cleaner Production, Vol. 135, 2016, pp. 701-711.

A.K. Yadav, H. Malik, S.S. Chandel,Application of rapid miner in ANN based prediction of solar radiation for assessment of solar energy resource potential of 76 sites in Northwestern India, Renewable and Sustainable Energy Reviews, Vol. 52, 2015, pp 1093-1106.

V. Prem, K. Uma Rao, Development of statistical time series models for solar power prediction, Renewable Energy, Vol. 83, 2015, pp 100-109.

C.Paoli, C Voyant, M. Muselli, M-L. Nivet, Multi-horizon Irradiation Forecasting For Mediterranean Locations Using Time Series Models, Energy Procedia, Vol. 57, 2014, pp. 1354-1363.

A. Kahaji, R. Alaoui, S. Farhat, A. Ihlal, L. Bouhouch,Modélisation de la prédiction de l'énergie solaire journalière par la méthode ARMA, TELECOM'2013 & 8ème JFMMA, Marrakech, Morocco, Mars 13-15, 2013.

C. Voyant, M. Muselli, C. Paoli, M-L. Nivet, Numerical weather prediction (NWP) and hybrid ARMA/ANN model to predict global radiation, Energy, Vol. 39, Issue 1, 2012, pp. 341-355.

C. Voyant, M. Muselli, C. Paoli, M.L. Nivet, Optimization of an artificial neural network dedicated to the multivariate forecasting of daily global irradiation, Energy, Vol. 36, Issue 1, 2011, pp. 348 359.

C. Voyant, Prédiction de séries temporelles de rayonnement solaire global et de production d'énergie photovoltaïque à partir de réseaux de neurones artificiels, Thesis, University of Corse-Pascal Paoli, 2011, pp. 91.

FO.Hocaoglu, Stochastic approach for daily solar radiation modeling,Solar Energy, n°85(2), 2011, pp. 278-287.

M.A. Behrang, E. Assareh, A. Ghanbarzadeh, A.R. Noghrehabadi, The Potential of Different Artificial Neural Network (ANN) Techniques in Daily Global Solar Radiation Modeling Based on Meteorological Data, Solar Energy, Vol. 84(8), 2010, pp. 1468 1480.

C. Paoli, C. Voyant, M. Muselli, M.L. Nivet, Solar Radiation Forecasting Using Qd-Hoc Time Series Preprocessing and Neural Networks, Proceedings of the 5th International Conference on Emerging Intelligent Computing Technology and applications, ICIC'09,Springer-Verlag Berlin, Heidelberg, 2009, pp. 898-907.

Y.Z. Li, J.C. Niu,Forecast of power generation for grid-connected photovoltaic system based on Markov chain, IEEE Asia-Pacific Power and Energy Engineering Conference, 2009, Vol. 1, pp. 652 655.

Y.Z. Li, J.C. Niu, Short-Term Forecast of Power Generation for Grid-Connected Photovoltaic System Based on Advanced Grey-Markov Chain, Energy and Environment Technology,2009. pp. 275-278.

A. Mellit, SA. Kalogirou, L. Hontoria, S. Shaari. Artificial intelligence techniques for sizing photovoltaic systems: A review. Renewable and Sustainable Energy Reviews,n°13-2, 2009, pp. 406-419.

A. Mellit, Artificial Intelligence technique for modelling and forecasting of solar radiation data: a review, Int. J. Artificial Intelligence and Soft Computing, Vol. 1, No. 1, 2008,pp. 52-76.

A. Mellit, S. Kalogirou, S. Shaari, H. Salhi et al. Methodology for predicting sequences of mean monthly clearness index and daily solar radiation data in remote areas: Application for sizing a stand-alone PV system, Renewable Energy, n°33(7), 2008, pp. 1570 1590.

A. Mellit, SA. Kalogirou. Artificial intelligence techniques for photovoltaic applications: A review. Progress in Energy and Combustion Science, n°1-1, 2008, pp. 52-76.

Hashmi, M., Hänninen, S., Mäki, K., Developing Smart Grid Concepts, Architectures and Technological Demonstrations Worldwide - A Literature Survey, (2013) International Review of Electrical Engineering (IREE), 8 (1), pp. 236-251.

Rajeev, T., Ashok, S., Architecture for Data Coordination Processing and Real Time Services in Smart Grid Environment, (2013) International Review on Modelling and Simulations (IREMOS), 6 (5), pp. 1680-1686.

Elmahni, L., Bouhouch, L., Alaoui, R., Moudden, A., Modeling and Control of a Hybrid Microgrid by Multi-Agent System, (2015) International Review of Electrical Engineering (IREE), 10 (1), pp. 145-153.

Farhat, S., Alaoui, M., Kahaji, A., Bouhouch, L., MPPT Efficiency Test by Neural Networks and P&O Algorithm, (2013) International Review of Electrical Engineering (IREE), 8 (5), pp. 1548-1555.

Web site:

MATLAB, Neural Network Toolbox User's Guide, TheMaths Works Inc., 1994-2012.

David A. Dickey, Wayne A. Fuller, Distribution of the Estimators for Autoregressive Time Series With a Unit Root, Journal of the American Statistical Association, Vol74, Issue 366, 1979, pp 427 431.

R. Davidson, James G. MacKinnon, Estimation and Inference in Econometrics, Oxford University Press, Inc., ISBN: 0-19-506011-3, 1993, pp. 701-733.

D. Kwiatkowski, P.C.B. Phillips, P. Schmidt, Y. Shin, Testing the Null Hypothesis of Stationarity against the Alternative of a Unit Root: How sure are we that economic time series have a unit root, Journal of Econometrics, Vol. 54, Issue 1-3, 1992, pp. 159-178.

G. Dreyfus, J.-M. Martinez, M. Samuelides, M.B. Gordon, F. Badran, S. Thiria, Apprentissage statistique, Groupe Eyrolles, ISBN: 978-2-212-12229-9, 2002, 2004, 2008, p. 77, 26 and 133.

John A. Duffie, William A. Beckman, Solar Engineering of Thermal processes, Second Edition, John Wiley, New York, 1991, pp. 3-45.


  • There are currently no refbacks.

Please send any question about this web site to
Copyright © 2005-2021 Praise Worthy Prize