forecasting of daily global radiation

This paper present s an application of Artificial Neural Networks (ANNs) to predict daily solar radiation . We look at the Multi -Layer Perceptron (MLP) network which is the most used of ANNs architectures. In previous studies, we have developed an ad -hoc time series preprocessing and optimized a MLP with endogenous inputs in order to forecast the solar radiation on a horizontal surface. W e propose in this paper to study the contributi on of exogenous meteorological data (multivariate method) as time series to our optimized MLP and compare with different forecasting methods: a naive forecaster (persi stence), AR IMA reference predictor , an ANN with preprocessing using only endogenous input s (univariate method) and an ANN with preprocessing using endogenous and exogenous inputs. The use of exogenous data generates a nRMSE decrease between 0.5% and 1% for two stations during 2006 and 2007 (Corsica Island, France) . T he prediction results are also relevant for the concrete case of a tilted PV wall (1.175 kWp) . The add ition of e ndogenous and exogenous data allow s a 1% decreas e of the nRMSE over a 6 months -cloudy period for the power production. While the use of exogenous data shows an interest in winter , endogenous data as inputs on a preprocessed ANN seem sufficient in summer .

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

[2]  Gérard Dreyfus,et al.  Flash Flood Forecasting by Statistical Learning in the Absence of Rainfall Forecast: A Case Study , 2009, EANN.

[3]  S. Yakowitz.  NEAREST‐NEIGHBOUR METHODS FOR TIME SERIES ANALYSIS , 1987 .

[4]  J. Mubiru,et al.  Estimation of monthly average daily global solar irradiation using artificial neural networks , 2008 .

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

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

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

[8]  Cyril Voyant,et al.  Solar Radiation Forecasting Using Ad-Hoc Time Series Preprocessing and Neural Networks , 2009, ICIC.

[9]  W. Beckman,et al.  Evaluation of hourly tilted surface radiation models , 1990 .

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

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

[12]  D. O. Logofet,et al.  The mathematics of Markov models: what Markov chains can really predict in forest successions. , 2000 .

[13]  Nitin Muttil,et al.  Machine-learning paradigms for selecting ecologically significant input variables , 2007, Eng. Appl. Artif. Intell..

[14]  Donald H. Burn,et al.  Simulating climate change scenarios using an improved K-nearest neighbor model , 2006 .

[15]  Yingni Jiang,et al.  Computation of monthly mean daily global solar radiation in China using artificial neural networks and comparison with other empirical models , 2009 .

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

[17]  A. Louche,et al.  First order Markov chain model for generating synthetic “typical days” series of global irradiation in order to design photovoltaic stand alone systems , 2001 .

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

[19]  Gilles Notton,et al.  PREDICTING HOURLY SOLAR IRRADIATIONS ON INCLINED SURFACES BASED ON THE HORIZONTAL MEASUREMENTS: PERFORMANCES OF THE ASSOCIATION OF WELL-KNOWN MATHEMATICAL MODELS , 2006 .

[20]  P. Ineichen,et al.  Ground-reflected radiation and albedo , 1990 .

[21]  J. Michalsky,et al.  Modeling daylight availability and irradiance components from direct and global irradiance , 1990 .

[22]  Cyril Voyant,et al.  Predictability of PV power grid performance on insular sites without weather stations: use of artificial neural networks , 2009, ArXiv.

[23]  Soteris A. Kalogirou,et al.  Artificial intelligence techniques for photovoltaic applications: A review , 2008 .

[24]  F. Hocaoglu,et al.  Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks , 2008 .

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

[26]  G. Kamali,et al.  Evaluation of 12 models to estimate hourly diffuse irradiation on inclined surfaces , 2008 .

[27]  Jesús Polo,et al.  Artificial intelligence techniques applied to hourly global irradiance estimation from satellite-derived cloud index , 2005 .

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

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

[30]  B. R. Menezes,et al.  Improving generalization of MLPs with sliding mode control and the Levenberg-Marquardt algorithm , 2007, Neurocomputing.

[31]  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 .

[32]  R. Kuhlemann,et al.  Rethinking satellite-based solar irradiance modelling: The SOLIS clear-sky module , 2004 .