Time series modeling and large scale global solar radiation forecasting from geostationary satellites data

When a territory is poorly instrumented, geostationary satellites data can be useful to predict global solar radiation. In this paper, we use geostationary satellites data to generate 2-D time series of solar radiation for the next hour. The results presented in this paper relate to a particular territory, the Corsica Island, but as data used are available for the entire surface of the globe, our method can be easily exploited to another place. Indeed 2-D hourly time series are extracted from the HelioClim-3 surface solar irradiation database treated by the Heliosat-2 model. Each point of the map have been used as training data and inputs of artificial neural networks (ANN) and as inputs for two persistence models (scaled or not). Comparisons between these models and clear sky estimations were proceeded to evaluate the performances. We found a normalized root mean square error (nRMSE) close to 16.5% for the two best predictors (scaled persistence and ANN) equivalent to 35-45% related to ground measurements. Finally in order to validate our 2-D predictions maps, we introduce a new error metric called the gamma index which is a criterion for comparing data from two matrixes in medical physics. As first results, we found that in winter and spring, scaled persistence gives the best results (gamma index test passing rate is respectively 67.7% and 86%), in autumn simple persistence is the best predictor (95.3%) and ANN is the best in summer (99.8%).

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

[2]  D. Njomo,et al.  On the reliability of HELIOSAT method: A comparison with experimental data , 2010 .

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

[4]  Simon J. Thomas,et al.  A comparison of four indices for combining distance and dose differences. , 2012, International journal of radiation oncology, biology, physics.

[5]  Tommy W. S. Chow,et al.  Effective feature selection scheme using mutual information , 2005, Neurocomputing.

[6]  F. Hocaoglu Stochastic approach for daily solar radiation modeling , 2011 .

[7]  D. Low,et al.  A technique for the quantitative evaluation of dose distributions. , 1998, Medical physics.

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

[9]  Diego G. Loyola,et al.  Applications of neural network methods to the processing of Earth observation satellite data , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[10]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

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

[12]  Roger Brugge,et al.  A comparison of the performance of Kalpana and Meteosat‐7 WV radiances in the ECMWF NWP model , 2011 .

[13]  Bernhard Geiger,et al.  Satellite Application Facilities irradiance products: hourly time step comparison and validation over Europe , 2009 .

[14]  Roger Saunders,et al.  ASSIMILATION OF METEOSAT RADIANCE DATA WITHIN THE 4 DVAR SYSTEM AT ECMWF , 2010 .

[15]  Brian Golding NumeriCal Weather prediCtioN (NWp) , 2012 .

[16]  A. Troccoli,et al.  Seasonal climate forecasting , 2010 .

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

[18]  M. Mueselli Utilization of Meteosat satellite-derived radiation data for integration of autonomous photovoltaic solar energy systems in remote areas , 1998 .

[19]  M. Ninyerola,et al.  Mapping a topographic global solar radiation model implemented in a GIS and refined with ground data , 2008 .

[20]  A. Louche,et al.  IMPROVED PROCEDURE FOR STAND-ALONE PHOTOVOLTAIC SYSTEMS SIZING USING METEOSAT SATELLITE IMAGES , 1998 .

[21]  Cyril Voyant,et al.  Multi-horizon solar radiation forecasting for Mediterranean locations using time series models , 2013, ArXiv.

[22]  Jan Kleissl,et al.  Solar Energy Forecasting and Resource Assessment , 2013 .

[23]  M. Muselli,et al.  Disaggregation of satellite derived irradiance maps: Evaluation of the process and application to Corsica , 2012 .

[24]  F. Kasten The linke turbidity factor based on improved values of the integral Rayleigh optical thickness , 1996 .

[25]  L. Wald,et al.  The method Heliosat-2 for deriving shortwave solar radiation from satellite images , 2004 .

[26]  Cyril Voyant,et al.  Hybrid methodology for hourly global radiation forecasting in Mediterranean area , 2012, ArXiv.

[27]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[28]  Hamdy K. Elminir,et al.  Prediction of hourly and daily diffuse fraction using neural network, as compared to linear regression models , 2007 .

[29]  O. Şenkal Modeling of solar radiation using remote sensing and artificial neural network in Turkey , 2010 .

[30]  Peter M. Inness,et al.  NWP Models – the Basic Principles , 2012 .

[31]  Cyril Voyant,et al.  PV output power fluctuations smoothing: The MYRTE platform experience , 2012 .

[32]  L. Wald,et al.  Worldwide Linke turbidity information , 2003 .

[33]  Viorel Badescu,et al.  Weather Modeling and Forecasting of PV Systems Operation , 2012 .

[34]  C. Gueymard Clear-sky irradiance predictions for solar resource mapping and large-scale applications: Improved validation methodology and detailed performance analysis of 18 broadband radiative models , 2012 .

[35]  Cyril Voyant,et al.  Hourly Global Radiation Prediction from Geostationary Satellite Data , 2013 .

[36]  Jörg Bendix,et al.  Satellite based remote sensing of weather and climate: recent achievements and future perspectives , 2011 .

[37]  Mohammad Ebrahim Banihabib,et al.  Comparative study of statistical and artificial neural network's methodologies for deriving global solar radiation from NOAA satellite images , 2013 .

[38]  L. Wald,et al.  On the clear sky model of the ESRA — European Solar Radiation Atlas — with respect to the heliosat method , 2000 .

[39]  Yılmaz Kaya,et al.  Comparison of ANN and MLR models for estimating solar radiation in Turkey using NOAA/AVHRR data , 2013 .

[40]  Antonios Marinopoulos,et al.  Installation of PV systems in Greece-Reliability improvement in the transmission and distribution system , 2010 .

[41]  Jean-Noël Thépaut,et al.  Assimilation of Meteosat radiance data within the 4D‐Var system at ECMWF: Assimilation experiments and forecast impact , 2004 .

[42]  Christophe Vernay,et al.  Characterizing measurements campaigns for an innovative calibration approach of the global horizontal irradiation estimated by HelioClim-3 , 2013 .

[43]  Nasser Mozayani,et al.  Mutual Information Based Input Variable Selection Algorithm and Wavelet Neural Network for Time Series Prediction , 2008, ICANN.

[44]  Richard P. Allan,et al.  Combining satellite data and models to estimate cloud radiative effect at the surface and in the atmosphere , 2011 .

[45]  S.F. Crone,,et al.  Stepwise Selection of Artificial Neural Network Models for Time Series Prediction , 2005 .

[46]  Jun Li,et al.  Mutual information algorithms , 2010 .