ANFIS-based estimation of PV module equivalent parameters: application to a stand-alone PV system with MPPT controller

The performance and system cost of photovoltaic (PV) systems can be improved by employing high-efficiency power conditioners with maximum power point tracking (MPPT) methods. Fast implementation and accurate operation of MPPT controllers can be realized by modeling the characteristics of PV modules, obtaining equivalent parameters. In this study, adaptive neuro-fuzzy inference systems (ANFISs) have been used to obtain 3 of the parameters in a single-diode model of PV cells, namely series resistance, shunt resistance, and diode ideality factor. The input parameters of ANFISs are a material-type of PV modules, short circuit current, open circuit voltage, and unit area under the I-V curve of the PV module. The advantage of the proposed method is that the equivalent parameters can be obtained for a wide range of PV modules of different types (monocrystalline, multicrystalline, and thin-film) using easily obtainable electrical parameters. To demonstrate the accuracy of the proposed model, MPPT control is implemented in a PV system with a battery charge application for 3 different types of PV modules. The obtained results suggest that the ANFIS model appears to be a useful tool for estimating the equivalent parameters of PV modules.