Estimation of Solar Irradiance using the measured parameters of the photovoltaic system by Artificial Neural Network

Abstract

This article aims to estimate irradiance using measured parameters from a real photovoltaic system. For this study, output current and voltage values were used from a set of solar panels with a capacity of 10 kW and a 10 kVA power inverter, which provide the necessary data for irradiance estimation. The data was collected at a sampling frequency of 15 seconds. To achieve this goal, an Artificial Neural Network (ANN) was applied to the reference data, which includes time series of solar irradiance, current, and voltage produced by the photovoltaic panels on different days of the year under varying weather conditions. Once the ANN is trained, its performance will be validated by comparing the estimation generated by the network with data from a reference cell on the days selected for the study. Additionally, the model will be evaluated using data from other days, not used in the training, to verify its ability to generalize under different meteorological conditions.