An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control

Abstract

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.

References in corpus (9)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Addressing Function Approximation Error in Actor-Critic Methods
• Benchmarking Deep Reinforcement Learning for Continuous Control
• A Review of Deep Reinforcement Learning for Smart Building Energy Management
• Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
• Building HVAC Scheduling Using Reinforcement Learning via Neural Network Based Model Approximation
• One for Many: Transfer Learning for Building HVAC Control
• Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning

Cited by in corpus (1)

• SINERGYM -- A virtual testbed for building energy optimization with Reinforcement Learning