An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control
This work addresses the problem of energy consumption and comfort optimization in HVAC systems for building managers and researchers, but it is incremental as it focuses on evaluation rather than introducing new methods.
The paper tackled the lack of standardization in evaluating Deep Reinforcement Learning (DRL) algorithms for HVAC control by conducting a reproducible assessment using the Sinergym framework, finding that algorithms like SAC and TD3 show potential in complex scenarios but face challenges in generalization and incremental learning.
Heating, Ventilation, and Air Conditioning (HVAC) systems are a major driver of energy consumption in commercial and residential buildings. Recent studies have shown that Deep Reinforcement Learning (DRL) algorithms can outperform traditional reactive controllers. However, DRL-based solutions are generally designed for ad hoc setups and lack standardization for comparison. To fill this gap, this paper provides a critical and reproducible evaluation, in terms of comfort and energy consumption, of several state-of-the-art DRL algorithms for HVAC control. The study examines the controllers' robustness, adaptability, and trade-off between optimization goals by using the Sinergym framework. The results obtained confirm the potential of DRL algorithms, such as SAC and TD3, in complex scenarios and reveal several challenges related to generalization and incremental learning.