Parameters Estimation of PV Models Using Artificial Neural Network

PV systems are widely installed and the building block to the solar system is the solar cell itself. In this paper, a new idea was presented, where Artificial Neural Network (ANN) was used to extract the five parameters of a solar module using only the basic voltage and current parameters. In addition, a large number of PV modules datasheet information was used to train an ANN to obtain the five parameters of any new module. In order to train the neural network (NN), particle swarm optimization technique was employed to obtain the input and output data set. Instead of five parameters of a solar module, only four parameters were used for the optimization technique and remaining was found from the direct equation.A comparison of Multilayer Perceptron and Radial Basis Function Neural Networks (NN) performance was provided. The proposed technique for solar cell parameters extraction was found robust, and accurate. Unlike parameter extraction for a specific panel, the proposed approach is a generalized approach that can extract the five parameters for any panel regardless its manufacturer. Using the mean square error and the squared error as measurement tools of the robustness of the proposed models, it has been found that the developed models are very accurate and robust.