Use of satellite data to improve solar radiation forecasting with Bayesian Artificial Neural Networks

Solar forecasting has become an important issue for power systems planning and operating, especially in islands grids. Power generation and grid utilities need day ahead, intra-day and intra-hour Global Horizontal solar Irradiance (GHI) forecasts for operations. In this paper, we focus on intra-day solar forecasting with forecast horizons ranging from 1 h to 6 h ahead. An Artificial Neural Networks (ANN) model is proposed to forecast GHI using ground measurement data and satellite data (from Helioclim-3) as inputs. In order to compare the forecasting results obtained by the proposed ANN model, we also include in this work a simple nai¨ve model, based on the persistence of the clear sky index (smart persistence model), as well as another reference model, the climatological mean model. The models were trained and tested for two ground measurements stations in Gran Canaria Island, Pozo (south) and Las Palmas (in the north). Firstly, ANN was trained and tested only with past ground measurement irradiance and compared by means of relative metrics with nai¨ve models. While this first step led to better performances, forecasting skills were improved by including exogenous inputs to the model by using GHI satellite data from surrounding area.

[1]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[2]  Tariq Muneer,et al.  Quality control of solar radiation data: Present status and proposed new approaches , 2005 .

[3]  T. Hoff,et al.  Validation of short and medium term operational solar radiation forecasts in the US , 2010 .

[4]  Philippe Lauret,et al.  Bayesian neural network approach to short time load forecasting , 2008 .

[5]  V. Badescu,et al.  Accuracy analysis for fifty-four clear-sky solar radiation models using routine hourly global irradiance measurements in Romania , 2013 .

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

[7]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[8]  R. Bird,et al.  Simplified clear sky model for direct and diffuse insolation on horizontal surfaces , 1981 .

[9]  T. Hoff,et al.  QUANTIFYING PV POWER OUTPUT VARIABILITY , 2010 .

[10]  Jorge Aguilera,et al.  Generation of hourly irradiation synthetic series using the neural network multilayer perceptron , 2002 .

[11]  Alfred Jean Philippe Lauret,et al.  A node pruning algorithm based on a Fourier amplitude sensitivity test method , 2006, IEEE Transactions on Neural Networks.

[12]  Richard Perez,et al.  Modeling PV fleet output variability , 2012 .

[13]  Carine Riviere,et al.  Bayesian and Sensitivity Analysis Approaches to Modeling the Direct Solar Irradiance , 2006 .

[14]  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 .

[15]  Carlos F.M. Coimbra,et al.  Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs , 2013 .

[16]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[17]  Markus Eck,et al.  Case Studies on the Use of Solar Irradiance Forecast for Optimized Operation Strategies of Solar Thermal Power Plants , 2008, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  J. Kleissl,et al.  Chapter 8 – Overview of Solar-Forecasting Methods and a Metric for Accuracy Evaluation , 2013 .

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

[20]  Rafael Montenegro,et al.  An adaptive solar radiation numerical model , 2012, J. Comput. Appl. Math..

[21]  Tariq Muneer,et al.  Clear-sky classification procedures and models using a world-wide data-base , 2007 .

[22]  L. Wald,et al.  McClear: a new model estimating downwelling solar radiation at ground level in clear-sky conditions , 2013 .

[23]  D. Boldo,et al.  Very short term forecasting of the Global Horizontal Irradiance using a spatio-temporal autoregressive model , 2014 .

[24]  Rafael Montenegro,et al.  Typical Meteorological Year (TMY) Evaluation for Power Generation in Gran Canaria Island, Spain , 2010 .

[25]  A. Hammer,et al.  Short-term forecasting of solar radiation: a statistical approach using satellite data , 1999 .

[26]  T. Soubdhan,et al.  A benchmarking of machine learning techniques for solar radiation forecasting in an insular context , 2015 .

[27]  Carlos F.M. Coimbra,et al.  On the role of lagged exogenous variables and spatio–temporal correlations in improving the accuracy of solar forecasting methods , 2015 .

[28]  John Boland,et al.  Post-processing of solar irradiance forecasts from WRF model at Reunion Island , 2014 .

[29]  Lucien Wald,et al.  The HelioClim Project: Surface Solar Irradiance Data for Climate Applications , 2011, Remote. Sens..

[30]  A. Smirnov,et al.  AERONET-a federated instrument network and data archive for aerosol Characterization , 1998 .

[31]  Detlev Heinemann,et al.  Prediction of Solar Irradiance and Photovoltaic Power , 2012 .

[32]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[33]  William D. Penny,et al.  Bayesian neural networks for classification: how useful is the evidence framework? , 1999, Neural Networks.

[34]  M. Diagne,et al.  Review of solar irradiance forecasting methods and a proposition for small-scale insular grids , 2013 .