Reinforcement learning for HVAC control and energy efficiency in residential buildings with BOPTEST simulations and real-case validation

The increasing emphasis on comfortable indoor environments, coupled with the challenges posed by climate change, demands innovative strategies for heating, ventilation, and air conditioning (HVAC) control. This paper proposes a Reinforcement Learning (RL)-based approach that not only enhances occupant comfort but also maximizes energy efficiency, thereby contributing to reduced greenhouse gas emissions. Leveraging the Building Optimization Testing (BOPTEST) platform for systematic validation, our methodology addresses the inherent complexity of indoor climates and building thermal dynamics. Simulation results show that the RL agent achieves up to 26.3% energy savings over a specified period, outperforming conventional Proportional-Integral (PI) controllers. Beyond simulation, an experimental case study was conducted in a residential building located in Mekn & egrave;s, Morocco, confirming the agent's adaptability under real-world conditions. Despite the shorter testing window, these trials demonstrated a further 8.8% reduction in energy consumption compared to a basic rule-based controller, reinforcing the RL agent's ability to balance thermal comfort and operational efficiency. By bridging this critical gap in HVAC control research, our work offers a transformative, data-driven strategy for achieving both sustainability and occupant well-being in residential buildings.