Multi-Objective Optimization of Energy Consumption and Thermal Comfort in Smart HVAC Systems Using Metaheuristic Algorithms

Abstract

The continuous growth of energy demand in the building sector has driven research toward intelligent and adaptive control systems capable of balancing energy efficiency and occupant comfort. Smart HVAC (Heating, Ventilation, and Air Conditioning) systems have emerged as a key component of energy-efficient building design, integrating real-time sensing, predictive control, and metaheuristic optimization algorithms. This study aims to develop and evaluate a multi-objective optimization framework that minimizes energy consumption while maximizing thermal comfort through the use of advanced metaheuristic algorithms such as NSGA-II, PSO, and GA. The proposed framework employs real operational data from smart buildings to assess the trade-off between energy usage and thermal comfort indices (PMV and PPD). Data from experimental and field measurements are incorporated to ensure realistic boundary conditions. The optimization results show that by adjusting HVAC control parameters dynamically, the overall energy consumption can be reduced by up to 23% while maintaining acceptable thermal comfort levels. The study also compares the performance of different algorithms, highlighting that NSGA-II achieves the most stable convergence and better Pareto-front diversity. Furthermore, a sensitivity analysis identifies temperature set-point range and air supply rate as the most influential variables affecting both comfort and energy demand. These findings confirm that the integration of metaheuristic optimization with IoT-based control can significantly enhance HVAC system efficiency, providing a scalable pathway toward zero-energy buildings and sustainable urban environments.