A comparison between BNN and regression polynomial methods for the evaluation of the effect of soiling in large scale photovoltaic plants

This paper presents a comparison between two different techniques for the determination of the effect of soiling on large scale photovoltaic plants. Four Bayesian Neural Network (BNN) models have been developed in order to calculate the performance at Standard Test Conditions (STCs) of two plants installed in Southern Italy before and after a complete clean-up of their modules. The differences between the STC power before and after the clean-up represent the losses due to the soiling effect. The results obtained with the BNN models are compared with the ones calculated with a well known regression model. Although the soiling effect can have a significant impact on the PV system performance and specific models developed are applicable only to the specific location in which the testing was conducted, this study is of great importance because it suggests a procedure to be used in order to give the necessary confidence to operation and maintenance personnel in applying the right schedule of clean-ups by making the right compromise between washing cost and losses in energy production.

[1]  Luis Marroyo,et al.  Soiling and other optical losses in solar‐tracking PV plants in navarra , 2011 .

[2]  S. Pelland,et al.  Estimating the uncertainty in long-term photovoltaic yield predictions , 2013 .

[3]  Adel Mellit,et al.  Prediction of daily global solar irradiation data using Bayesian neural network: A comparative study , 2012 .

[4]  R. Gottschalg,et al.  Effect of shading caused by dust on Cadmium Telluride photovoltaic modules , 2011, 2011 37th IEEE Photovoltaic Specialists Conference.

[5]  A. Kimber,et al.  The Effect of Soiling on Large Grid-Connected Photovoltaic Systems in California and the Southwest Region of the United States , 2006, 2006 IEEE 4th World Conference on Photovoltaic Energy Conference.

[6]  M. AbdulHadi,et al.  Neuro-fuzzy-based solar cell model , 2004, IEEE Transactions on Energy Conversion.

[7]  Dave Winkler,et al.  Bayesian Regularization of Neural Networks , 2009, Artificial Neural Networks.

[8]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[9]  Francesco Grimaccia,et al.  Photovoltaic plants predictive model by means of ANN trained by a hybrid evolutionary algorithm , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[10]  Soteris A. Kalogirou,et al.  On-site PV characterization and the effect of soiling on their performance , 2013 .

[11]  Cyril Voyant,et al.  Bayesian rules and stochastic models for high accuracy prediction of solar radiation , 2013, ArXiv.

[12]  R. L. Hammond,et al.  Effects of soiling on PV module and radiometer performance , 1997, Conference Record of the Twenty Sixth IEEE Photovoltaic Specialists Conference - 1997.

[13]  Thomas R. Betts,et al.  Dust‐induced shading on photovoltaic modules , 2014 .

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

[15]  Syed A.M. Said,et al.  Effects of dust accumulation on performances of thermal and photovoltaic flat-plate collectors , 1990 .

[16]  Jagdish C. Patra,et al.  Neural network‐based model for dual‐junction solar cells , 2011 .

[17]  B. Marion,et al.  Performance parameters for grid-connected PV systems , 2005, Conference Record of the Thirty-first IEEE Photovoltaic Specialists Conference, 2005..

[18]  A. Mellit,et al.  The effect of soiling on energy production for large-scale photovoltaic plants , 2011 .

[19]  S. Bouzid,et al.  Effects of sandblasting on the efficiencies of solar panels , 2000 .

[20]  Antonio Luque,et al.  Handbook of photovoltaic science and engineering , 2011 .

[21]  S. Yamashiro,et al.  Novel Distributed Power Generating System of PV-ECaSS Using Solar Energy Estimation , 2007, IEEE Transactions on Energy Conversion.

[22]  Didier Mayer,et al.  Performance Prediction of Grid-Connected Photovoltaic Systems Using Remote Sensing , 2008 .

[23]  Bodo Littmann,et al.  Direct monitoring of energy lost due to soiling on first solar modules in California , 2012, 2012 IEEE 38th Photovoltaic Specialists Conference (PVSC) PART 2.

[24]  Toshiyuki Sueyoshi,et al.  Photovoltaic power stations in Germany and the United States: A comparative study by data envelopment analysis , 2014 .

[25]  Huey Pang,et al.  Study on Effect of Urban Pollution to Performance of Commercial Copper Indium Diselenide Modules , 2006, 2006 IEEE 4th World Conference on Photovoltaic Energy Conference.

[26]  Detlev Heinemann,et al.  Monitoring and remote failure detection of grid-connected PV systems based on satellite observations , 2007 .