Predicting the Single Diode Model Parameters using Machine Learning Model

Abstract

The increasing energy demands, requires the usage of solar photovoltaic (SPV) more largely. The work focuses on the Single Diode Model (SDM) of solar panels with the help of five parameters namely series resistance (Rse), shunt resistance (Rsh), diode ideality factor (A), light generated current (ILG), and diode reverse saturation current (Isat). To identify unknown parameters, modeling is done by deriving the equations and initial values are assumed under Standard Test Conditions (STC). The deviations of Rse and Rsh values are very less when the experimented and analytical values of the AlokP module are compared. The predicted values hold good for the panel and show that the NR (Newton Raphson) method is simple, robust, and computationally less intensive. With the help of NR methodology, the dataset is created for various solar panels. The proposed methodology is checked with various other PV (Photovoltaic) models and the best-fit machine learning model is predicted. The unknown values are predicted under cross-out validation and hold-out validation methods and the best-fit machine learning model is identified by checking the least RMSE (Root Mean Squared Error) value. Nineteen machine learning models are compared and the model with the minimum RMSE value is chosen to the best-fit model.