System identification with cross validation technique for modeling inverter of photovoltaic system

In this paper, modeling of one type of grid connected single phase inverter commercially available in Thailand is carried out. An inverter of a grid-connected photovoltaic system has been tested and its model determined. The inverter operates in six steady state conditions and its modeling is done using nonlinear system identification approach with Hammerstein Wiener Model. The models with no cross validation and cross validation data of six steady state conditions have been experimented. The results comparison on modeling by using cross validation and no cross validation data has been analyzed by model order, model accuracies and model error. The average percentage accuracy of system identification with cross validation data and no cross validation is 81.89 and 63.83 respectively.

[1]  George C. Verghese,et al.  Modeling and simulation of power electronic converters , 2001, Proc. IEEE.

[2]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[3]  Anawach Sangswang,et al.  Modeling of single phase inverter of photovoltaic system using Hammerstein–Wiener nonlinear system identification , 2010 .

[4]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[5]  Torbjörn Wigren.  User choices and model validation in system identification using nonlinear Wiener models , 2003 .

[6]  K. Uosaki,et al.  Block oriented nonlinear model identification by evolutionary computation approach , 2003, Proceedings of 2003 IEEE Conference on Control Applications, 2003. CCA 2003..

[7]  Trevor S. Wiens,et al.  Three way k-fold cross-validation of resource selection functions , 2008 .

[8]  Slobodan Cuk,et al.  A general unified approach to modelling switching-converter power stages , 1977 .

[9]  Chi K. Tse,et al.  Complex behavior in switching power converters , 2002, Proc. IEEE.

[10]  P. Zumel,et al.  Black-box modeling of three phase voltage source inverters based on transient response analysis , 2010, 2010 Twenty-Fifth Annual IEEE Applied Power Electronics Conference and Exposition (APEC).

[11]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[12]  B. Muenpinij,et al.  Modeling of Single Phase Inverter of Photovoltaic System Using System Identification , 2010, 2010 Second International Conference on Computer and Network Technology.

[13]  R. Dennis Cook,et al.  Cross-Validation of Regression Models , 1984 .

[14]  Chang-Xue Jack Feng,et al.  Threefold vs. fivefold cross validation in one-hidden-layer and two-hidden-layer predictive neural network modeling of machining surface roughness data , 2005 .

[15]  Agostino Di Ciaccio,et al.  Computational Statistics and Data Analysis Measuring the Prediction Error. a Comparison of Cross-validation, Bootstrap and Covariance Penalty Methods , 2022 .

[16]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[17]  F. Alonge,et al.  Nonlinear Modeling of DC/DC Converters Using the Hammerstein's Approach , 2007, IEEE Transactions on Power Electronics.

[18]  Andrew W. Moore,et al.  Hoeffding Races: Accelerating Model Selection Search for Classification and Function Approximation , 1993, NIPS.

[19]  P. Burman.  A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods , 1989 .

[20]  Georg Bretthauer,et al.  Identification of MISO Wiener and Hammerstein systems , 2003, 2003 European Control Conference (ECC).

[21]  Frederick Mosteller,et al.  A $k$-Sample Slippage Test for an Extreme Population , 1948 .