Conference Agenda

Modern heating, ventilation, and air conditioning (HVAC) systems account for between 40% and up to 60% of the total energy consumption in commercial and residential buildings, which presents significant opportunities for optimization through intelligent control strategies. Traditional HVAC control systems operate reactively, adjusting only to the set temperature without considering energy consumption patterns or optimization. This study develops a comprehensive mathematical model of HVAC energy consumption that serves as a dynamic input variable for advanced control systems, enabling predictive climate control with energy-awareness. The proposed methodology integrates artificial neural networks for hourly energy consumption prediction, considering city-specific meteorological variables, HVAC equipment parameters, indoor characteristics of the conditioned space, and real consumption data from HVAC systems across 34 brands, 70 models, 9 BTU/h capacities, and 4 compressor technologies, including On-Off, Inverter, Digital Inverter, and Dual Inverter. The model combines thermodynamic principles with machine learning techniques to predict real-time energy consumption. This research contributes to the development of intelligent and energy-efficient HVAC systems, essential for the transition toward sustainable buildings.