Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC control
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Controlling heating, ventilation and air-conditioning (HVAC) systems is crucial to improving demand-side energy efficiency. At the same time, the thermodynamics of buildings and uncertainties regarding human activities make effective management challenging. While the concept of model-free reinforcement learning demonstrates various advantages over existing strategies, the literature relies heavily on value-based methods that can hardly handle complex HVAC systems. This paper conducts experiments to evaluate four actor-critic algorithms in a simulated data centre. The performance evaluation is based on their ability to maintain thermal stability while increasing energy efficiency and on their adaptability to weather dynamics. Because of the enormous significance of practical use, special attention is paid to data efficiency. Compared to the model-based controller implemented into EnergyPlus, all applied algorithms can reduce energy consumption by at least 10% by simultaneously keeping the hourly average temperature in the desired range. Robustness tests in terms of different reward functions and weather conditions verify these results. With increasing training, we also see a smaller trade-off between thermal stability and energy reduction. Thus, the Soft Actor Critic algorithm achieves a stable performance with ten times less data than on-policy methods. In this regard, we recommend using this algorithm in future experiments, due to both its interesting theoretical properties and its practical results.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625
Markov decision processes: Discrete stochastic dynamic programming
Hazeghi, K., & Puterman, M. L. (1995) · Journal of the American Statistical Association · doi:10.2307/2291177 · Cited by 8,037
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 7×
“DQN [22] Off-policy Discrete (12) – – A2C [45] On-policy Discrete/Continuous (D.”
MethodInfluentialSoft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor
Haarnoja, T., Zhou, A., Abbeel, P., & Levine, S. (2018) · arXiv · doi:10.48550/arxiv.1801.01290 · Cited by 5,594 · cited 4×
“on the following two algorithms: TD3 [48] and SAC [49].”
BackgroundMethodInfluentialAddressing Function Approximation Error in Actor-Critic Methods
Fujimoto, S., van Hoof, H., & Meger, D. (2018) · arXiv · doi:10.48550/arxiv.1802.09477 · Cited by 3,650 · cited 5×
“The policy uses delayed updates, as described in [48] for educed training time.”
BackgroundMethodInfluentialDeep Reinforcement Learning with Double Q-Learning
Van Hasselt, H., Guez, A., & Silver, D. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10295 · Cited by 3,318
Soft Actor-Critic Algorithms and Applications
Haarnoja, T., Zhou, A., Hartikainen, K., Tucker, G., Ha, S., Tan, J., Kumar, V., Zhu, H., Gupta, A., Abbeel, P., et al. (2018) · arXiv · doi:10.48550/arxiv.1812.05905 · Cited by 1,994 · cited 3×
“The gradient of this loss can be computed analytically and strongly resembles the DDPG update (16) (see [53] for the exact expression).”
BackgroundMethodInfluential
Cited by
Reinforcement learning for HVAC control in intelligent buildings: A technical and conceptual review
Al Sayed, K., Boodi, A., Sadeghian Broujeny, R., & Beddiar, K. (2024) · Journal of Building Engineering · doi:10.1016/j.jobe.2024.110085 · Cited by 140
Evaluation of advanced control strategies for building energy systems
Stoffel, P., Maier, L., Kümpel, A., Schreiber, T., & Müller, D. (2023) · Energy and Buildings · doi:10.1016/j.enbuild.2022.112709 · Cited by 126
“Biemann et al. ([75]) apply a SAC algorithm to optimize the operation of a simulated data center HVAC system.”
Adesanya, M. A., Obasekore, H., Rabiu, A., Na, W.-H., Ogunlowo, Q. O., Akpenpuun, T. D., Kim, M.-H., Kim, H.-T., Kang, B.-Y., & Lee, H.-W. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124126 · Cited by 72
Metadata
- Authors
- Biemann, M., Scheller, F., Liu, X., & Huang, L.
- Venue
- Applied Energy
- Publisher
- Elsevier BV
- Published
- 2021-09
- Volume
- 298
- Pages
- 117164
- ISSN
- 0306-2619 (ISSN-L)
- OpenAlex
- W3166166623
- Cited by
- 188
- References
- 13
- FWCI
- 11.66
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC control. https://app.cochat.ai/papers/10.1016/j.apenergy.2021.117164
- The paper
- Biemann, M., Scheller, F., Liu, X., & Huang, L. (2021). Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC control. Applied Energy. https://doi.org/10.1016/j.apenergy.2021.117164
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.