COMPARATIVE ANALYSIS ON THE PREDICTION PERFORMANCE OF STATISTICAL MODELS AND NEURAL NETWORKS. A CASE STUDY BASED ON ENERGY CONSUMPTION FROM RENEWABLE SOURCES

The main technologies used for residential purposes are power generation systems and solutions to reduce consumption, respectively, the implementation of smart management systems that could schedule the operation of the smart grid appliances by switching off the appliance for an energy saving condition when not in use. The challenge that power providers face at peak times is optimizing power consumption from smart grids. These considerations have a considerable impact on the power system's reliability. This article aims to forecast energy consumption from photovoltaic (PV) sources by implementing and comparing three different predictive models to improve interpretability, accuracy, and computational efficiency. The models selected in this approach are: ARIMA (Auto Regressive Integrated Moving Average), a statistical model for linear dependencies and trends; SARIMA (Seasonal ARIMA), an extension of ARIMA for seasonal fluctuations; and NAR (Nonlinear Auto Regressive Neural Network), a machine learning model for nonlinear relationships. The performance of these techniques is tested and confirmed using a dataset of real measurements related to the energy from photovoltaic sources' consumption, monitored at 15-minute intervals in 2024. The added value of the proposed approach consists of proving how improved forecasting directly contributes to energy efficiency and loss reduction in PV systems by enabling better energy management and demand-response strategies.