Artificial intelligence-based solar radiation forecasting for energy optimization in sustainable buildings

Abstract

The work presented in this article aligns with our university's commitment to advancing renewable energy sources. We can better plan and optimize energy use if we are aware of the factors that affect solar energy generation. This study examines the application of artificial neural networks (ANNs) in forecasting global horizontal irradiance (GHI) within the context of sustainable energy. The primary objective is to enhance the accuracy and reliability of solar irradiance forecasts, thereby improving the performance of renewable energy systems, such as concentrated solar power (CSP). This article provides an overview of solar radiation, the physical factors that influence its distribution, and the impact of panel tilt angle on energy production. It presents a case study in Morocco, which uses a hybrid approach to predict solar radiation. The results demonstrate that ANN, employing advanced machine learning (ML) methods, provides more accurate and reliable forecasts than traditional models. This advance could improve energy planning, reduce uncertainty, and enable better management of solar energy production and storage systems. Our results suggest that this approach has increased forecast accuracy.