Safe Reinforcement Learning for Buildings: Minimizing Energy Use While Maximizing Occupant Comfort

作者：M. Hassan Esmaeili, Sascha Hammes, Samuele Tosatto, David Geisler‐Moroder, P Zech · 发表于：Energies · 年份：2025 · DOI：10.3390/en18195313 · 被引用次数：11 · 研究领域：Building Energy and Comfort Optimization、Infection Control and Ventilation、Noise Effects and Management

With buildings accounting for 40% of global energy consumption, heating, ventilation, and air conditioning (HVAC) systems represent the single largest opportunity for emissions reduction, consuming up to 60% of commercial building energy while maintaining occupant comfort. This critical balance between energy efficiency and human comfort has traditionally relied on rule-based and model predictive control strategies. Given the multi-objective nature and complexity of modern HVAC systems, these approaches fall short in satisfying both objectives. Recently, reinforcement learning (RL) has emerged as a method capable of learning optimal control policies directly from system interactions without requiring explicit models. However, standard RL approaches frequently violate comfort constraints during exploration, making them unsuitable for real-world deployment where occupant comfort cannot be compromised. This paper addresses two fundamental challenges in HVAC control: the difficulty of constrained optimization in RL and the challenge of defining appropriate comfort constraints across diverse conditions. We adopt a safe RL with a neural barrier certificate framework that (1) transforms the constrained HVAC problem into an unconstrained optimization and (2) constructs these certificates in a data-driven manner using neural networks, adapting to building-specific comfort patterns without manual threshold setting. This approach enables the agent to almost guarantee solutions that impr...