24-hours ahead global irradiation forecasting using Multi-Layer Perceptron

The grid integration of variable renewable energy sources implies that their effective production could be predicted, at different times ahead. In the case of solar plants, the driving factor is the global solar irradiation (sum of direct and diffuse solar radiation projected on a plane (Wh/m²)). This paper focuses on the 24-hours ahead forecast of global solar irradiation (i.e. hourly solar irradiation prediction for the day after). A method based on artificial intelligence using Artificial Neural Network (ANN) is reported. The ANN hereafter considered is a Multi-Layer Perceptron (MLP) applied to a pre-treated time series (TS). Two architectures are tested; it is shown that the most relevant is based on a multi-output MLP using endogenous and exogenous input data. A real case 2-years TS is computed and the MLP results are compared with both a statistical approach (AutoRegressive-Moving Average model; ARMA) and a reference persistent approach. Results show that the prediction error estimate (nRMSE) can be reduced by 1.3 points with an ANN compared to ARMA and by 7.8 points compared to the naive persistence.

[1]  Athanasios Sfetsos,et al.  Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques , 2000 .

[2]  Guoqiang Peter Zhang,et al.  Trend Time–Series Modeling and Forecasting With Neural Networks , 2008, IEEE Transactions on Neural Networks.

[3]  Adel Mellit,et al.  Radial Basis Function Network-based prediction of global solar radiation data: Application for sizing of a stand-alone photovoltaic system at Al-Madinah, Saudi Arabia , 2010 .

[4]  Yoshifusa Ito,et al.  Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory , 1991, Neural Networks.

[5]  Lucas Alados-Arboledas,et al.  Neural network for the estimation of UV erythemal irradiance using solar broadband irradiance , 2007 .

[6]  James D. Hamilton.  Time Series Analysis , 1994 .

[7]  Rob J Hyndman,et al.  25 years of time series forecasting , 2006 .

[8]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

[9]  Chia-Yon Chen,et al.  Technology forecasting and patent strategy of hydrogen energy and fuel cell technologies , 2011 .

[10]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[11]  Cyril Voyant,et al.  Forecasting of preprocessed daily solar radiation time series using neural networks , 2010 .

[12]  Ken Nagasaka,et al.  Neural Network Ensemble-Based Solar Power Generation Short-Term Forecasting , 2009, J. Adv. Comput. Intell. Intell. Informatics.

[13]  A. Moreno-Munoz,et al.  Very short term forecasting of solar radiation , 2008, 2008 33rd IEEE Photovoltaic Specialists Conference.

[14]  Samuel S. P. Shen,et al.  A new analysis of variability and predictability of seasonal rainfall of central southern Africa for 1950–94 , 2004 .

[15]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[16]  J. Mubiru.  Predicting total solar irradiation values using artificial neural networks , 2008 .

[17]  M. Guerra‒Balcázar,et al.  Glycerol oxidation in a microfluidic fuel cell using Pd/C and Pd/MWCNT anodes electrodes , 2013 .

[18]  Jenq-Neng Hwang,et al.  Handbook of Neural Network Signal Processing , 2000, IEEE Transactions on Neural Networks.

[19]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[20]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[21]  A. Franco,et al.  Strategies for optimal penetration of intermittent renewables in complex energy systems based on techno-operational objectives , 2011 .

[22]  Elfatih A. B. Eltahir,et al.  The role of clouds in the surface energy balance over the Amazon forest , 1998 .

[23]  G. Dreyfus,et al.  Réseaux de neurones - Méthodologie et applications , 2002 .

[24]  Mohammad Bagher Tavakoli,et al.  Modified Levenberg-Marquardt Method for Neural Networks Training , 2007 .

[25]  S. H. Cao,et al.  Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis , 2006 .

[26]  Dennis A. Ahlburg,et al.  Error measures and the choice of a forecast method , 1992 .

[27]  S.W.H. de Haan,et al.  Optimal energy management strategy and system sizing method for stand-alone photovoltaic-hydrogen systems , 2008 .

[28]  Gabriel López,et al.  Selection of input parameters to model direct solar irradiance by using artificial neural networks , 2004 .

[29]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[30]  Annegret Gratzki,et al.  Estimates of global radiation at the ground from the reduced data sets of the international satellite cloud climatology project , 1987 .

[31]  Soteris A. Kalogirou,et al.  Artificial intelligence techniques for sizing photovoltaic systems: A review , 2009 .

[32]  A. Mellit,et al.  A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy , 2010 .

[33]  M. Ranjan,et al.  Solar resource estimation using artificial neural networks and comparison with other correlation models , 2003 .

[34]  P. Seferlis,et al.  Power management strategies for a stand-alone power system using renewable energy sources and hydrogen storage , 2009 .

[35]  P. Ineichen.  A broadband simplified version of the Solis clear sky model , 2008 .

[36]  Roberto Quiroz,et al.  Atmospheric transmissivity: distribution and empirical estimation around the central Andes , 2004 .

[37]  Saleh M. Al-Alawi,et al.  An ANN-based approach for predicting global radiation in locations with no direct measurement instrumentation , 1998 .

[38]  Jenn-Jiang Hwang.  Policy review of greenhouse gas emission reduction in Taiwan , 2011 .

[39]  Marc Muselli,et al.  Multicriteria decision aiding for selection of photovoltaic plants on farming fields in Corsica Island (France) , 2010 .

[40]  A. Ghanbarzadeh,et al.  The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data , 2010 .

[41]  Cyril Voyant,et al.  Numerical Weather Prediction (NWP) and hybrid ARMA/ANN model to predict global radiation , 2012, ArXiv.

[42]  Gabriel López,et al.  Daily solar irradiation estimation over a mountainous area using artificial neural networks , 2008 .

[43]  Eleonora D'Andrea,et al.  24-hour-ahead forecasting of energy production in solar PV systems , 2011, 2011 11th International Conference on Intelligent Systems Design and Applications.

[44]  Nikolaos Kourentzes,et al.  Feature selection for time series prediction - A combined filter and wrapper approach for neural networks , 2010, Neurocomputing.

[45]  Cyril Voyant,et al.  Optimization of an artificial neural network dedicated to the multivariate forecasting of daily glob , 2011 .

[46]  Guoqiang Peter Zhang,et al.  Neural network forecasting for seasonal and trend time series , 2005, Eur. J. Oper. Res..

[47]  Mustafa Gölcü,et al.  Daily means ambient temperature prediction using artificial neural network method: A case study of Turkey , 2009 .

[48]  M. Santarelli,et al.  Design and analysis of stand-alone hydrogen energy systems with different renewable sources , 2004 .

[49]  K. Sumathy,et al.  Potential of renewable hydrogen production for energy supply in Hong Kong , 2006 .

[50]  P. Ineichen.  Comparison of eight clear sky broadband models against 16 independent data banks , 2006 .

[51]  Constantinos S. Pattichis,et al.  Classification of rainfall variability by using artificial neural networks , 2001 .