Abstract
This paper introduces a novel method for representing the photovoltaic (PV) characteristics using Takagi–Sugeno type neuro-fuzzy network (NF). The proposed NF uses four layers with sixty-four fuzzy rules. Moreover, an improved self-tuning method is developed based on the PV system and its high-performance requirements, to adjust the parameters of the fuzzy logic in order to minimize the square of the error between actual and reference outputs. The developed PV model has a compact structure, an interpretable set of rules and ultimately is accurate in predicting the output values for given input samples. The NF-PV model has been applied for reconstructing a set of practical current–voltage characteristics, and it has been shown to compare well with the measured values. The proposed approach can also be used to predict and extract the maximum power points of individual PV modules in real time. Numerical and experimental data have confirmed its accuracy.
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 call
