E. Caro Huertas, J. Juan Ruiz, J. Cara Cañas
Accurate electricity demand forecasting is essential for power system planning and operation. In Spain, hourly day-ahead prices, set by the marginalist market, may influence consumer behavior and affect demand patterns. This study analyzes the impact of electricity prices on demand forecasting accuracy by assessing their role as predictive variables. We examine whether incorporating price data improves forecasting performance using machine learning techniques, particularly Random Forest. Through a comparative analysis of models with and without price variables, we explore the extent to which price fluctuations shape demand dynamics and enhance predictive capabilities.
Palabras clave: Electricity demand forecasting, day-ahead market, machine learning, random forest
Programado
Optimization and Learning in Energy
11 de junio de 2025 15:30
Auditorio 2. Leandre Cristòfol