An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916376318312448 |
|---|---|
| author | Manjavacas, Antonio Campoy-Nieves, Alejandro Jiménez-Raboso, Javier Molina-Solana, Miguel Gómez-Romero, Juan |
| author_facet | Manjavacas, Antonio Campoy-Nieves, Alejandro Jiménez-Raboso, Javier Molina-Solana, Miguel Gómez-Romero, Juan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05737 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control Manjavacas, Antonio Campoy-Nieves, Alejandro Jiménez-Raboso, Javier Molina-Solana, Miguel Gómez-Romero, Juan Machine Learning Systems and Control I.2.8; J.2 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. |
| title | An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control |
| topic | Machine Learning Systems and Control I.2.8; J.2 |
| url | https://arxiv.org/abs/2401.05737 |