Human-in-the-Loop AI for HVAC Management Enhancing Comfort and Energy Efficiency
Open accessThe DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
Heating, Ventilation, and Air Conditioning (HVAC) systems account for approximately 38% of building energy consumption globally, making them one of the most energy-intensive services.The increasing emphasis on energy efficiency and sustainability, combined with the need for enhanced occupant comfort, presents a significant challenge for traditional HVAC systems.These systems often fail to dynamically adjust to real-time changes in electricity market rates or individual comfort preferences, leading to increased energy costs and reduced comfort.In response, we propose a Human-inthe-Loop (HITL) Artificial Intelligence framework that optimizes HVAC performance by incorporating real-time user feedback and responding to fluctuating electricity prices.Unlike conventional systems that require predefined information about occupancy or comfort levels, our approach learns and adapts based on ongoing user input.By integrating the occupancy prediction model with reinforcement learning, the system improves operational efficiency and reduces energy costs in line with electricity market dynamics, thereby contributing to demand response initiatives.Through simulations, we demonstrate that our method achieves significant cost reductions compared to baseline approaches while maintaining or enhancing occupant comfort.This feedback-driven approach ensures personalized comfort control without the need for predefined settings, offering a scalable solution that balances individual preferences with economic and environmental goals.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Liang et al. proposed a human-in-the-loop AI system for HVAC management that meets both efficiency and comfort requirements.”
From Human-in-the-Loop Artificial Intelligence: A Systematic Review of Concepts, Methods, and Applications (2026) · cites this paper as [42]
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
1 retracted
Popa, D., Pop, F., Serbanescu, C., & Castiglione, A. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3724-6 · Cited by 82 · cited 3×
“These systems monitor environmental conditions, energy usage patterns, and localized renewable generation such as PV to provide feedback and suggestions to users, encouraging them to adopt more energy-efficient habits [3, 21, 26, 30, 31].”
RetractedProximal 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
Baxter, L. A. (1995) · Technometrics · doi:10.1080/00401706.1995.10484354 · Cited by 2,415
A review on buildings energy information: Trends, end-uses, fuels and drivers
González-Torres, M., Pérez-Lombard, L., Coronel, J. F., Maestre, I. R., & Yan, D. (2022) · Energy Reports · doi:10.1016/j.egyr.2021.11.280 · Cited by 1,036
A review of data-driven approaches for prediction and classification of building energy consumption
Wei, Y., Zhang, X., Shi, Y., Xia, L., Pan, S., Wu, J., Han, M., & Zhao, X. (2018) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2017.09.108 · Cited by 803
Yao, Y., & Shekhar, D. K. (2021) · Building and Environment · doi:10.1016/j.buildenv.2021.107952 · Cited by 447 · cited 1×
“As global energy demands rise and sustainability initiatives become more important, optimizing HVAC systems has become a priority for reducing both operational costs and environmental impact [16, 38].”
Model predictive HVAC load control in buildings using real-time electricity pricing
Avci, M., Erkoc, M., Rahmani, A., & Asfour, S. (2013) · Energy and Buildings · doi:10.1016/j.enbuild.2013.01.008 · Cited by 232 · cited 1×
“This variability leads to periods of both surplus and scarcity, resulting in fluctuations in electricity prices and supply-demand imbalances [5, 8].”
Occupancy behavior based model predictive control for building indoor climate—A critical review
Mirakhorli, A., & Dong, B. (2016) · Energy and Buildings · doi:10.1016/j.enbuild.2016.07.036 · Cited by 225 · cited 1×
“These systems autonomously reduce heating or cooling during unoc-cupied periods and increase output as needed to maintain set-points [12, 17, 24, 27].”
Thermal comfort and use of thermostats in Finnish homes and offices
Karjalainen, S. (2009) · Building and Environment · doi:10.1016/j.buildenv.2008.09.002 · Cited by 194 · cited 1×
“Other studies indicate that despite relying on complex thermal dynamic models, 15–28% of occupants remain dissatisfied with indoor conditions, even when they have control over the temperature setpoints [4, 22].”
Jazizadeh, F., Ghahramani, A., Becerik-Gerber, B., Kichkaylo, T., & Orosz, M. (2014) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000300 · Cited by 190 · cited 1×
“These systems autonomously reduce heating or cooling during unoc-cupied periods and increase output as needed to maintain set-points [12, 17, 24, 27].”
A stochastic computer model for heating and cooling loads
Mortensen, R. E., & Haggerty, K. P. (1988) · IEEE Transactions on Power Systems · doi:10.1109/59.14584 · Cited by 164 · cited 2×
“Weadopt athermalmodel[25] that conditions the next indoor temperature 𝑇 in 𝑡 + 1 on three variables: current indoor temperature 𝑇 in , outdoor temperature 𝑇 out , and the controlled action 𝑎 𝑐𝑡 at time 𝑡 .”
A review of reinforcement learning methodologies for controlling occupant comfort in buildings
Han, M., May, R., Zhang, X., Wang, X., Pan, S., Yan, D., Jin, Y., & Xu, L. (2019) · Sustainable Cities and Society · doi:10.1016/j.scs.2019.101748 · Cited by 162 · cited 1×
“As global energy demands rise and sustainability initiatives become more important, optimizing HVAC systems has become a priority for reducing both operational costs and environmental impact [16, 38].”
ARAS Human Activity Datasets in Multiple Homes with Multiple Residents
Alemdar, H., Durmaz Incel, O., Ertan, H., & Ersoy, C. (2013) · Proceedings of the ICTs for improving Patients Rehabilitation Research Techniques · doi:10.4108/icst.pervasivehealth.2013.252120 · Cited by 148
A Decentralized Electricity Market Scheme Enabling Demand Response Deployment
Bahrami, S., Amini, M. H., Shafie‐khah, M., & Catalào, J. P. S. (2017) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2017.2771279 · Cited by 148 · cited 1×
“The quadratic relationship between temperature deviation and discomfort probability reflects the nonlinear nature of human thermal comfort perception, where discomfort increases more rapidly as temperatures deviate further from the preferred set-point [9, 13, 40].”
Constantopoulos, P., Schweppe, F. C., & Larson, R. C. (1991) · Computers & Operations Research · doi:10.1016/0305-0548(91)90013-h · Cited by 146 · cited 1×
“The quadratic relationship between temperature deviation and discomfort probability reflects the nonlinear nature of human thermal comfort perception, where discomfort increases more rapidly as temperatures deviate further from the preferred set-point [9, 13, 40].”
A comprehensive review of the applications of machine learning for HVAC
Zhou, S., Shah, A. A., Leung, P., Zhu, X., & Liao, Q. (2023) · DeCarbon · doi:10.1016/j.decarb.2023.100023 · Cited by 138 · cited 1×
“These limitations result in higher operating costs and reduced occupant comfort [37, 41].”
The effect of wind and solar power generation on wholesale electricity prices in Australia
Csereklyei, Z., Qu, S., & Ancev, T. (2019) · Energy Policy · doi:10.1016/j.enpol.2019.04.007 · Cited by 137 · cited 1×
“As renewable energy sources like solar and wind increasingly penetrate the energy market, their intermittent nature introduces greater variability into the grid, driven by weather conditions and time of day [14, 23].”
Yu, L., Xie, D., Huang, C., Jiang, T., & Zou, Y. (2018) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2018.2875727 · Cited by 92 · cited 1×
“The quadratic relationship between temperature deviation and discomfort probability reflects the nonlinear nature of human thermal comfort perception, where discomfort increases more rapidly as temperatures deviate further from the preferred set-point [9, 13, 40].”
Shuvo, S. S., & Yılmaz, Y. (2022) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2022.3158814 · Cited by 81 · cited 1×
“Shuvo and Yilmaz [34] develop a Home Energy Recommendation System (HERS) that applies deep reinforcement learning (RL) to manage energy consumption in smart appliances including HVAC.”
Optimal price based control of HVAC systems in multizone office buildings for demand response
Amin, U., Hossain, M. J., & Fernandez, E. (2020) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2020.122059 · Cited by 79 · cited 1×
“This variability leads to periods of both surplus and scarcity, resulting in fluctuations in electricity prices and supply-demand imbalances [5, 8].”
Energy-related values and satisfaction levels of residential and office building occupants
Amasyali, K., & El-Gohary, N. (2015) · Building and Environment · doi:10.1016/j.buildenv.2015.08.005 · Cited by 74 · cited 1×
“Other studies indicate that despite relying on complex thermal dynamic models, 15–28% of occupants remain dissatisfied with indoor conditions, even when they have control over the temperature setpoints [4, 22].”
Ranjan, J., & Scott, J. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2971648.2971659 · Cited by 73 · cited 1×
“In these advanced comfort models, user preferences are inferred through environmental sensors that track environmental factors such as temperature and humidity, cloth insulation, and even physiological indicators like skin temperature and heart rate [1, 11, 18, 20, 29, 39].”
Cheng, X., Yang, B., Olofsson, T., Liu, G., & Li, H. (2017) · Building and Environment · doi:10.1016/j.buildenv.2017.05.021 · Cited by 66 · cited 1×
“In these advanced comfort models, user preferences are inferred through environmental sensors that track environmental factors such as temperature and humidity, cloth insulation, and even physiological indicators like skin temperature and heart rate [1, 11, 18, 20, 29, 39].”
Pritoni, M., Woolley, J., & Modera, M. P. (2016) · Energy and Buildings · doi:10.1016/j.enbuild.2016.05.024 · Cited by 62
REHAB-C: Recommendations for Energy HABits Change
Sardianos, C., Varlamis, I., Dimitrakopoulos, G., Anagnostopoulos, D., Alsalemi, A., Bensaali, F., Himeur, Y., & Amira, A. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.05.041 · Cited by 61
Vision-based thermal comfort quantification for HVAC control
Jung, W., & Jazizadeh, F. (2018) · Building and Environment · doi:10.1016/j.buildenv.2018.05.018 · Cited by 60 · cited 1×
“In these advanced comfort models, user preferences are inferred through environmental sensors that track environmental factors such as temperature and humidity, cloth insulation, and even physiological indicators like skin temperature and heart rate [1, 11, 18, 20, 29, 39].”
Kar, P., Shareef, A., Kumar, A., Harn, K. T., Kalluri, B., & Panda, S. K. (2019) · Building and Environment · doi:10.1016/j.buildenv.2019.01.035 · Cited by 53 · cited 1×
“These systems monitor environmental conditions, energy usage patterns, and localized renewable generation such as PV to provide feedback and suggestions to users, encouraging them to adopt more energy-efficient habits [3, 21, 26, 30, 31].”
Endorsing domestic energy saving behavior using micro-moment classification
Alsalemi, A., Ramadan, M., Bensaali, F., Amira, A., Sardianos, C., Varlamis, I., & Dimitrakopoulos, G. J. (2019) · Applied Energy · doi:10.1016/j.apenergy.2019.05.089 · Cited by 52
Maniatis, G. I., & Milonas, N. T. (2022) · Energy Policy · doi:10.1016/j.enpol.2022.113243 · Cited by 51
Sensing Occupant Comfort Using Wearable Technologies
Abdallah, M., Clevenger, C. M., Vu, T. N., & Nguyen, A. D. (2016) · ASCE Construction Research Congress (CRC) · doi:10.1061/9780784479827.095 · Cited by 40 · cited 1×
“In these advanced comfort models, user preferences are inferred through environmental sensors that track environmental factors such as temperature and humidity, cloth insulation, and even physiological indicators like skin temperature and heart rate [1, 11, 18, 20, 29, 39].”
Chojecki, A., Rodak, M., Ambroziak, A., & BORKOWSKI, P. (2019) · IET Smart Grid · doi:10.1049/iet-stg.2019.0005 · Cited by 38 · cited 1×
“These systems autonomously reduce heating or cooling during unoc-cupied periods and increase output as needed to maintain set-points [12, 17, 24, 27].”
Chen, L., Meng, F., & Zhang, Y. (2023) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2023.3251302 · Cited by 32
Real-time personalised energy saving recommendations
Sardianos, C., Chronis, C., Varlamis, I., Dimitrakopoulos, G. J., Himeur, Y., Alsalemi, A., Bensaali, F., & Amira, A. (2020) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics50389.2020.00072 · Cited by 27 · cited 2×
“These systems monitor environmental conditions, energy usage patterns, and localized renewable generation such as PV to provide feedback and suggestions to users, encouraging them to adopt more energy-efficient habits [3, 21, 26, 30, 31].”
Facial Skin Temperature as a Proactive Variable in a Building Thermal Comfort Control System
Yi, B., & Choi, J.-H. (2015) · doi:10.1061/9780784479681.013 · Cited by 17 · cited 1×
“In these advanced comfort models, user preferences are inferred through environmental sensors that track environmental factors such as temperature and humidity, cloth insulation, and even physiological indicators like skin temperature and heart rate [1, 11, 18, 20, 29, 39].”
Can computers visually quantify human thermal comfort?
Jazizadeh, F., & Pradeep, S. (2016) · ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) · doi:10.1145/2993422.2993571 · Cited by 17 · cited 1×
“In these advanced comfort models, user preferences are inferred through environmental sensors that track environmental factors such as temperature and humidity, cloth insulation, and even physiological indicators like skin temperature and heart rate [1, 11, 18, 20, 29, 39].”
John, C., Vallianos, C., Candanedo, J., & Athienitis, A. (2018) · Healthy, Intelligent and Resilient Buildings and Urban Environments · doi:10.14305/ibpc.2018.ps17 · Cited by 17 · cited 1×
“50 hours, which aligns with typical residential building time constants ranging from 15 to 55 hours observed in [19].”
Research works printed but not linked: 2
- ANSI Ashrae et al. 2020. Standard 55-2020: Thermal environmental conditions for human occupancy. American Society of Heating, Refrigerating, and Air-Conditioning Engineers, Inc. Atlanta.
- Olli Seppanen William J Fisk and QH Lei. 2006. Room temperature and productivity in office work. Healthy Buildings 2006 Conference 1 (2006) 243–247.
Cited by
Lazaros, K., Vrahatis, A. G., & Kotsiantis, S. (2026) · Entropy · doi:10.3390/e28040377 · Cited by 50
Felez, R., & Mindán, J. F. (2026) · Applied Sciences · doi:10.3390/app16042006 · Cited by 19
Yu, D., Tao, Q., Liu, Q., Jin, Y., Sun, Y., & Fu, P. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.105706 · Cited by 25
An, S., Qiu, J., Lin, J., Yuan, Z., Tian, W., & Yao, Z. (2026) · Energy internet. · doi:10.1049/ein2.70021 · Cited by 7
“Humans participate in EMS not merely as overseers but as active contributors of knowledge, context, and preferences [82].”
Bai, Y., Liang, X., Huang, C., Zheng, J., Yang, F., & Wang, H. (2026) · Current Sustainable/Renewable Energy Reports · doi:10.1007/s40518-026-00293-0 · Cited by 1
“A recent study [58] incorporates occupancy patterns into HVAC control using human-in-the-loop artificial intelligence (AI), enabling energy manage - ment to adapt to human behaviors and real-time feedback for improved efficiency and comfort.”
Self-citation
Metadata
- Authors
- Liang, X., de Nijs, F., Say, B., & Wang, H.
- Affiliations
- Monash University (AU)
- Monash University, Melbourne, Australia
- Venue
- Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems
- Publisher
- ACM
- Published
- 2025-06-16
- Pages
- 359-370
- OpenAlex
- W4411345873
- Cited by
- 14
- References
- 35
- Citations by year
- 2026: 11 · 2025: 3
- FWCI
- 46.34
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- ACM International Conference on Future Energy Systems (e-Energy) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Monash University Research Portal (Monash University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Australian Research Council (DE230100046)
- ARC Training Centre in Optimisation Technologies, Integrated Methodologies and Applications (IC200100009)
- Topics
- Physical Sciences › Engineering › Building and Construction › Building Energy and Comfort Optimization
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Smart Grid Energy Management
- Physical Sciences › Engineering › Mechanical Engineering › Refrigeration and Air Conditioning Technologies
- Keywords
- human-in-the-loop AI, HVAC control, building energy efficiency, occupant comfort, electricity price fluctuation, demand response, occupancy prediction, reinforcement learning, real-time user feedback
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
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.