Master optimization process based on neural networks ensemble for 24-h solar irradiance forecast

In the paper two models implemented to forecast the hourly solar irradiance with a day in advance are described. The models, based on Artificial Neural Networks (ANN), are generated by a master optimization process that defines the best number of neurons and selects a suitable ensemble of ANN. The two models consist of a Statistical (ST) model that uses only local measured data and a Model Output Statistics (MOS) that corrects Numerical Weather Prediction (NWP) data. ST and MOS are tested for the University of Rome “Tor Vergata” site. The models are trained and validated using one year data. Through a cross training procedure, the dependence of the models on the training year is also analyzed. The performance of ST, NWP and MOS models, together with the benchmark Persistence Model (PM), are compared. The ST model and the NWP model exhibit similar results. Nevertheless different sources of forecast errors between ST and NWP models are identified. The MOS model gives the best performance, improving the forecast of approximately 29% with respect to the PM.

[1]  Fei Wang,et al.  Short-Term Solar Irradiance Forecasting Model Based on Artificial Neural Network Using Statistical Feature Parameters , 2012 .

[2]  Chul-Hwan Kim,et al.  Application of neural network to 24-hour-ahead generating power forecasting for PV system , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

[3]  Stefano Serafini,et al.  Outdoor ESTER test facility for advanced technologies PV modules , 2008, 2008 33rd IEEE Photovoltaic Specialists Conference.

[4]  J. A. Ruiz-Arias,et al.  Comparison of numerical weather prediction solar irradiance forecasts in the US, Canada and Europe , 2013 .

[5]  Jiacong Cao,et al.  Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks , 2008 .

[6]  Richard Perez,et al.  Forecasting solar radiation – Preliminary evaluation of an approach based upon the national forecast database , 2007 .

[7]  C. Coimbra,et al.  Forecasting of global and direct solar irradiance using stochastic learning methods, ground experiments and the NWS database , 2011 .

[8]  Gerald Steinmaurer,et al.  Solar Irradiance Forecasting, Benchmarking of Different Techniques and Applications of Energy Meteorology , 2010 .

[9]  Hans-Georg Beyer,et al.  Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems , 2009, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[10]  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 .

[11]  J. Remund,et al.  Advances in Radiation Forecast Based on Regional Weather Models MM5 and WRF , 2010 .

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

[13]  Clifford W. Hansen,et al.  Global horizontal irradiance clear sky models : implementation and analysis. , 2012 .

[14]  J. A. Ruiz-Arias,et al.  Benchmarking of different approaches to forecast solar irradiance , 2009 .

[15]  Na Zhang,et al.  Photovoltaic system power forecasting based on combined grey model and BP neural network , 2011, 2011 International Conference on Electrical and Control Engineering.

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

[17]  Tomonobu Senjyu,et al.  Application of neural network to 24-hour-ahead generating power forecasting for PV system , 2008, PES 2008.

[18]  Marcel Suri,et al.  D 1.1.3 Report on Benchmarking of Radiation Products , 2009 .

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

[20]  Bangyin Liu,et al.  Online 24-h solar power forecasting based on weather type classification using artificial neural network , 2011 .

[21]  Cyril Voyant,et al.  Twenty four hours ahead global irradiation forecasting using multi‐layer perceptron , 2014 .

[22]  Gianpaolo Vitale,et al.  Solar Radiation Estimate and Forecasting by Neural Networks for Smart Grid Energy Management , 2013 .

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

[24]  Cyril Voyant,et al.  24-hours ahead global irradiation forecasting using Multi-Layer Perceptron , 2013 .

[25]  Chen Changsong,et al.  Forecasting power output for grid-connected photovoltaic power system without using solar radiation measurement , 2010, The 2nd International Symposium on Power Electronics for Distributed Generation Systems.

[26]  Gianpaolo Vitale,et al.  Solar Radiation Estimate and Forecasting by Neural Networks-based Approach , 2013 .

[27]  Gabi Friesen,et al.  Outdoor PV module performance comparison at two different locations , 2010 .

[28]  P. Ineichen,et al.  A new airmass independent formulation for the Linke turbidity coefficient , 2002 .

[29]  Xiaoyan Xu,et al.  Comparative study of power forecasting methods for PV stations , 2010, 2010 International Conference on Power System Technology.

[30]  Markus Voelter,et al.  State of the Art , 1997, Pediatric Research.

[31]  Davide Strepparava,et al.  Global Irradiance in the Southern Alpine Climate: Meteo Modelling and Statistical Post-Processing , 2013 .