Abstract
In the photovoltaic (PV) field, the outdoor evaluation of a PV system is quite complex, due to the variations of temperature and irradiance. In fact, the diagnosis of the PV modules is extremely required in order to maintain the optimum performance. In this paper, an artificial neural network (ANN) is proposed to build and train the model, and evaluate the PV module performance by mean bias error, mean square error and the regression analysis. We take temperature, irradiance and a specific voltage for input, and a specific current value for output, repeat several times in order to obtain an I-V curve. The main feature lies to the data-driven black-box method, with the ignorance of any analytical equations and hence the conventional five parameters (serial resistance, shunt resistance, non-ideal factor, reverse saturation current, and photon current). The ANN is able to predict the I-V curves of the Si PV module at arbitrary irradiance and temperature. Finally, the proposed algorithm has proved to be valid in terms of comparison with the testing dataset.
Highlights
Manufacturers provide standard reporting conditions (SRC) or standard test conditions (STC)ratings for photovoltaic (PV) components
Energy collection optimization of PV modules based on SRC efficiency is tough and misleading for actual weather conditions, proper characterization of the electrical performance (I-V curve) of PV modules is a basic requirement of PV engineering [1]
The most widely used single diode analytical model is based on the equivalent circuit which is composed of a current source, a diode, a series resistance, and a shunt resistance
Summary
Manufacturers provide standard reporting conditions (SRC) or standard test conditions (STC). The performance of analytical methods depends on the parameter accuracy, while the the data-driven artificial neural network (ANN) algorithm abandons the predominated parameters data-driven artificial neural network (ANN) algorithm abandons the predominated parameters and and equivalent circuit, and is able to build the PV model from historical data with no assumption. ANN is used to predict the I-V curve is used to predict the I-V curve of single crystal silicon modules under different irradiances and of single crystal silicon modules under different irradiances and temperatures without any parameters, temperatures without any parameters, and the prediction accuracy is proved to be better than the and the prediction accuracy is proved to be better than the parameter based method. The technical characteristics of the experimental device device used in this paper and the related data sets are introduced.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
