Integrative Forecasting of Solar Energy Production and Demand in Saudi Arabia using Machine Learning

Abstract

Balancing power generation and demand is a critical challenge in large-scale renewable energy systems. This paper focuses on energy forecasting for demand and supply in Saudi Arabia, leveraging a high-resolution dataset encompassing solar energy production from the country’s first large-scale solar plant and the energy demand of a nearby city. Advanced machine learning models are developed and evaluated to predict energy supply and demand patterns, addressing the inherent variability of renewable energy sources. The models effectively utilise historical and weather-related data to deliver accurate forecasts, enabling optimised planning and integration of renewable energy into the grid. This research contributes to advancing energy forecasting techniques for large-scale systems, enhancing sustainability and reliability in Saudi Arabia’s renewable energy sector.