Title: Data-Driven Forecasting and Optimization in Energy Systems with GUROBI

Abstract: This tutorial introduces participants to data-driven methods for forecasting and optimization in energy systems. We begin with supply and demand modelling, demonstrating how linear regression can be used for demand prediction. Building on this, we explore the role of feature importance in forecasting with Random Forest and analyse forecast results using K-means clustering. Furthermore, we continue with paradigms of data-driven optimization, focusing on the dynamic nature of external data and how it can be integrated to introduce temporality in the objective function and constraint. Participants will gain hands-on experience integrating external data and forecast outputs into Gurobi models using Python, illustrating how predictive analytics and mathematical optimization can be combined to support decision-making in energy applications.