Model Identification for Photovoltaic Panels Using Neural Networks

The present work documents the study on the usage of Neural Networks to compute the parameters used in solar panel modelling. The approach followed starts from a dataset obtained by a process of model identification via numerical solution of nonlinear equations. After a preliminary analysis pointing out the intrinsic difficulty in the classic identification of the parameters via NN, by taking advantage of closed form relations, a hybrid neural system, composed by neural network based identifiers and explicit equations, was implemented. The generalization capabilities of the neural identifier were investigated, showing the effectiveness of this approach.

[1]  Marcello Artioli,et al.  Numerical method for the extraction of photovoltaic module double-diode model parameters through cluster analysis , 2010 .

[2]  G. Capizzi,et al.  A neural network approach for the differentiation of numerical solutions of 3-D electromagnetic problems , 2004, IEEE Transactions on Magnetics.

[3]  A. Laudani,et al.  Reduced-form of the photovoltaic five-parameter model for efficient computation of parameters , 2013 .

[4]  Nate Blair,et al.  Comparison of Photovoltaic Models in the System Advisor Model: Preprint , 2013 .

[5]  Alessandro Salvini,et al.  Automatic and Parallel Optimized Learning for Neural Networks performing MIMO Applications , 2013 .

[6]  William A. Beckman,et al.  Improvement and validation of a model for photovoltaic array performance , 2006 .

[7]  B.M. Wilamowski,et al.  Neural network architectures and learning algorithms , 2009, IEEE Industrial Electronics Magazine.

[8]  Michael T. Manry,et al.  Minimizing validation error with respect to network size and number of training epochs , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

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

[10]  D. Carroll,et al.  Evaluation of methods to extract parameters from current–voltage characteristics of solar cells , 2013 .

[11]  Yi-Hua Liu,et al.  Neural-network-based maximum power point tracking methods for photovoltaic systems operating under fast changing environments , 2013 .

[12]  Alessandro Salvini,et al.  A neural networks-based maximum power point tracker with improved dynamics for variable dc-link grid-connected photovoltaic power plants , 2013 .

[13]  Javier Cubas,et al.  On the analytical approach for modeling photovoltaic systems behavior , 2014 .

[14]  A. K. Al-Othman,et al.  Simulated Annealing algorithm for photovoltaic parameters identification , 2012 .

[15]  Hao Yu,et al.  Selection of Proper Neural Network Sizes and Architectures—A Comparative Study , 2012, IEEE Transactions on Industrial Informatics.

[16]  Alireza Rezazadeh,et al.  Artificial bee swarm optimization algorithm for parameters identification of solar cell models , 2013 .

[17]  Fengzhu Ji,et al.  Finite-Element Neural Network-Based Solving 3-D Differential Equations in MFL , 2012, IEEE Transactions on Magnetics.

[18]  Amit Kumar Yadav,et al.  Solar radiation prediction using Artificial Neural Network techniques: A review , 2014 .

[19]  Alessandro Salvini,et al.  A Neural Network-Based Low-Cost Solar Irradiance Sensor , 2014, IEEE Transactions on Instrumentation and Measurement.

[20]  Mohammad Ali Abido,et al.  Parameter estimation for five- and seven-parameter photovoltaic electrical models using evolutionary algorithms , 2013, Appl. Soft Comput..

[21]  Ju-Jang Lee,et al.  Training Two-Layered Feedforward Networks With Variable Projection Method , 2008, IEEE Transactions on Neural Networks.

[22]  Salvatore Coco,et al.  Very Fast and Accurate Procedure for the Characterization of Photovoltaic Panels from Datasheet Information , 2014 .

[23]  Joni-Kristian Kämäräinen,et al.  Differential Evolution Training Algorithm for Feed-Forward Neural Networks , 2003, Neural Processing Letters.

[24]  Kay Chen Tan,et al.  Estimating the Number of Hidden Neurons in a Feedforward Network Using the Singular Value Decomposition , 2006, IEEE Trans. Neural Networks.

[25]  Alessandro Salvini,et al.  Learning optimization of neural networks used for MIMO applications based on multivariate functions decomposition , 2012 .

[26]  A. Sellami,et al.  Identification of PV solar cells and modules parameters using the genetic algorithms: Application to maximum power extraction , 2010 .

[27]  Antonino Laudani,et al.  High performing extraction procedure for the one-diode model of a photovoltaic panel from experimental I–V curves by using reduced forms , 2014 .

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

[29]  Kashif Ishaque,et al.  An improved modeling method to determine the model parameters of photovoltaic (PV) modules using differential evolution (DE) , 2011 .

[30]  D. Maskell,et al.  Parameter estimation of solar cells and modules using an improved adaptive differential evolution algorithm , 2013 .