Artificial Intelligence-Enabled Heating, Ventilation, and Air Conditioning Systems Toward Zero-Emission Buildings: A Systematic Review of Applications, Challenges, and Future Directions
Source abstract
Abstract
Heating, ventilation, and air conditioning (HVAC) systems are among the largest energy consumers in buildings, making their intelligent operation fundamental to achieving zero-emission performance and advancing climate neutrality. With recent progress in artificial intelligence (AI), new opportunities have emerged to optimize HVAC operations by enabling predictive, adaptive, and autonomous control. Several studies have explored aspects of AI-driven net-zero emission performance for building HVAC systems. However, a systematic assessment that consolidates these findings and identifies future directions is still needed. This review addresses this gap by analyzing the current state of research on AI-enabled HVAC systems in the context of zero-emission building performance, with particular attention to residential, commercial, and educational settings. In addition, it provides recommendations for future research while underscoring the importance of AI methods in achieving zero-emission performance of building HVAC systems. Based on this review, five primary application domains of AI-enabled building HVAC systems were identified and analyzed: predictive maintenance, scheduling, adaptive optimization, renewable energy integration, and IoT-enabled control. Existing research gaps are identified, including privacy-preserving AI methods, modular and interoperable frameworks, climate-adaptive and occupant-aware strategies, and computationally efficient architectures. Future directions in the field of the AI-enabled HVAC system integrations, along with lifecycle assessment, are highlighted to enable resilient, zero-emission building performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Building Energy and Comfort Optimization · Wind and Air Flow Studies · Refrigeration and Air Conditioning Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Université Clermont Auvergne, Clermont Auvergne INP, CNRS, Institut Pascal, F-63000 Clermont–Ferrand, France
Laboratoire Polytech’Lab (POLYTECH’LAB), Université Côte d’Azur, Polytech Nice Sophia, BP 145, Sophia Antipolis, 06903 Vallauris, France
References (100+)
Show source-provided references
1. (2025, June 30). IEA, Buildings: A Source of Enormous Untapped Efficiency Potential. Available online: https://www.iea.org/energy-system/buildings.
2. Hybrid solar-wind renewable energy systems with energy storage for net/nearly zero energy buildings: An uncertainty-based robust design10.1016/j.energy.2024.133965 ↗
3. Global estimation of building-integrated façade and rooftop photovoltaic potential by integrating 3D building footprint and spatio-temporal datasets10.1016/j.ynexs.2025.100060 ↗
4. Advancing the net zero emission building concept: Integrating photovoltaics and electrical storage for NZEB environmental performance in different energy and climate contexts10.1016/j.solener.2025.113331 ↗
5. Adams, M., Burrows, V., and Richardson, S. (2025, May 01). Bringing Embodied Carbon Upfront: Coordinated Action for the Building and Construction Sector to Tackle Embodied Carbon. Report by World Green Building Council. Available online: https://worldgbc.org/climate-action/embodied-carbon/#:~:text=By%202030%2C%20all%20new%20buildings,are%20net%20zero%20operational%20carbon.
6. Towards net-zero energy/emission buildings for sustainable development10.1016/j.esd.2024.101448 ↗
7. Experience on the application of aground source heat pump system in an archives building10.1016/j.enbuild.2011.08.029 ↗
8. A comparative thermodynamic and economic analysis and assessment of a conventional HVAC and a VRF system in a social and cultural center building10.1016/j.enbuild.2017.02.008 ↗
9. Emedo, C., Wada, O.Z., David-Olawade, A.C., Ling, J., Esan, D.T., Ijiwade, J., and Olawade, D.B. (2025). AI-driven transformations in smart buildings: A review of energy efficiency and sustainable operations. Digit. Eng., 100068.10.1016/j.dte.2025.100068 ↗
10. Comparing the life cycle costs of a traditional and a smart HVAC control system for Australian office buildings10.1016/j.jobe.2024.109686 ↗
11. A review of occupancy detection techniques for HVAC control: Advanced and practical challenges10.1016/j.jobe.2025.113962 ↗
12. Carbon capture, utilization and storage in buildings: Analysis of performance, social acceptance, policy measures, and the role of artificial intelligence10.1016/j.buildenv.2025.112817 ↗
13. Optimising building heat load prediction using advanced control strategies and artificial intelligence for HVAC system10.1016/j.tsep.2024.102484 ↗
14. Exploring the comprehensive integration of artificial intelligence in optimizing HVAC system operations: A review and future outlook10.1016/j.rineng.2024.103765 ↗
15. Applications of artificial intelligence for energy efficiency throughout the building lifecycle: An overview10.1016/j.enbuild.2024.113903 ↗
16. Reinforcement learning for HVAC control in intelligent buildings: A technical and conceptual review10.1016/j.jobe.2024.110085 ↗
17. Zero Energy Building—A review of definitions and calculation methodologies10.1016/j.enbuild.2010.12.022 ↗
18. A review of Net Zero Energy Buildings with reflections on the Australian context10.1016/j.enbuild.2017.10.055 ↗
19. A review of net zero energy buildings in hot and humid climates: Experience learned from 34 case study buildings10.1016/j.rser.2019.109303 ↗
20. A review of performance of zero energy buildings and energy efficiency solutions10.1016/j.jobe.2019.100772 ↗
21. Toward comprehensive zero energy building definitions: A literature review and recommendations10.1080/14786451.2020.1796664 ↗
22. Advances Toward a Net-Zero Global Building Sector10.1146/annurev-environ-012420-045843 ↗
23. Comparative review of international approaches to net-zero buildings: Knowledge-sharing initiative to develop design strategies for greenhouse gas emissions reduction10.1016/j.esd.2022.10.005 ↗
24. Data-driven prediction and optimization toward net-zero and positive-energy buildings: A systematic review10.1016/j.buildenv.2023.110578 ↗
25. Optimizing NZEB performance: A review of design strategies and case studies10.1016/j.rineng.2025.103950 ↗
26. Synergistic integration of digital twins and zero energy buildings for climate change mitigation in sustainable smart cities: A systematic review and novel framework10.1016/j.enbuild.2025.115484 ↗
27. Review of global advances towards net-zero emissions buildings10.1016/j.enbuild.2022.112142 ↗
28. Towards zero carbon, resilient, and community-integrated smart schools and campuses: A review10.1016/j.wds.2024.100193 ↗
29. Building energy technologies towards achieving net-zero pathway: A comprehensive review, challenges and future directions10.1016/j.jobe.2025.111795 ↗
30. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews10.1136/bmj.n71 ↗
31. A novel deep reinforcement learning based methodology for short-term HVAC system energy consumption prediction10.1016/j.ijrefrig.2019.07.018 ↗
32. Yuan, Y., Shim, J., Lee, S., Song, D., and Kim, J. (2020). Prediction for overheating risk based on deep learning in a zero energy building. Sustainability, 12.10.3390/su12218974 ↗
33. Artificial intelligence method for the forecast and separation of total and HVAC loads with application to energy management of smart and NZE homes10.1109/ACCESS.2021.3129172 ↗
34. Fault detection and diagnosis for the screw chillers using multi-region XGBoost model10.1080/23744731.2021.1877966 ↗
35. Diagnosis for multiple faults of chiller using ELM-KNN model enhanced by multi-label learning and specific feature combinations10.1016/j.buildenv.2022.108904 ↗
36. Knowledge-infused deep learning diagnosis model with self-assessment for smart management in HVAC systems10.1016/j.energy.2022.125969 ↗
37. Integrated passive design method optimized for carbon missions, economics, and thermal comfort of zero-carbon buildings10.1016/j.energy.2024.131048 ↗
38. Long-term analysis of cooling demand and heat recovery in hotel HVAC systems: Implications for sustainable chiller design and operation to reduce CO2 emissions10.1016/j.enbuild.2024.114657 ↗
39. Predicting the energy consumption of a VRF heat pump using manufacturer performance data and limited experimentation of dynamic data collection10.1016/j.enbuild.2023.113798 ↗
40. Assessing the accuracy of AI approaches for CO2 emission predictions in buildings10.1016/j.jclepro.2025.145692 ↗
41. Building energy prediction model with AI-based PSO-ANN approach integrating architectural and HVAC processes10.1016/j.buildenv.2025.113305 ↗
42. Motuziene, V., Bielskus, J., Dziugaite-Tumeniene, R., and Raudonis, V. (2025). Occupancy-based predictive AI-driven ventilation control for energy savings in office buildings. Sustainability, 17.10.3390/su17094140 ↗
43. A review of fault detection and diagnosis methods for residential air conditioning systems10.1016/j.buildenv.2019.106236 ↗
44. Ahmed, M.S., Mohamed, A., Homod, R.Z., and Shareef, H. (2016). Hybrid LSA-ANN based home energy management scheduling controller for residential demand response strategy. Energies, 9.10.3390/en9090716 ↗
45. Javaid, S., Abdullah, M., Javaid, N., Sultana, T., Ahmed, J., and Sattar, N.A. (2019, January 24–28). Towards buildings energy management: Using seasonal schedules under time of use pricing tariff via deep neuro-fuzzy optimizer. Proceedings of the 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), Tangier, Morocco.10.1109/IWCMC.2019.8766673 ↗
46. Incorporating deep learning of load predctions to enhance the optimal active energy management of combined cooling, heating and power system10.1016/j.energy.2021.121134 ↗
47. Xu, W., Li, Y., He, G., Xu, Y., and Gao, W. (2023). Performance assessment and comparative analysis of photovoltaic-battery system scheduling in an existing zero-energy house based on Reinforcement learning control. Energies, 16.10.3390/en16134844 ↗
48. Net-Zero Scheduling of Multi-Energy Building Energy Systems: A Learning-Based Robust Optimization Approach with Statistical Guarantees10.1109/TSTE.2024.3437210 ↗
49. Smart building transferable energy scheduling employing reward shaping deep reinforcement learning with demand side energy management10.1016/j.jobe.2025.112316 ↗
50. Integrated energy system scheduling strategy for zero-energy buildings based on MC-TD3 algorithm10.1016/j.jobe.2025.112920 ↗
51. Leveraging the machine learning techniques for demand-side flexibility—A comprehensive review10.1016/j.epsr.2024.111185 ↗
52. Optimal price based control of HVAC systems in multizone office buildings for demand response10.1016/j.jclepro.2020.122059 ↗
53. Yayla, A., Swierczewska, K.S., Kaya, M., Karaca, B., Arayici, Y., Ayozen, Y.E., and Tokdemir, O.B. (2022). Artificial intelligence (AI)-based occupant-centric heating ventilation and air conditioning (HVAC) control system for multi-zone commercial buildings. Sustainability, 14.10.3390/su142316107 ↗
54. ECO-FOCUS: Integrating computer vision and machine learning for personalized comfort prediction and adaptive HVAC control in office buildings10.1016/j.jobe.2025.113613 ↗
55. Three-objective optimization of the HVAC system control strategy in an educational building to reduce energy consumption and enhance indoor environmental quality (IEQ) using machine learning techniques10.1016/j.jobe.2025.112444 ↗
56. Energy optimization for HVAC systems in multi-VAV open offices: A deep reinforcement learning approach10.1016/j.apenergy.2023.122354 ↗
57. Online learning-enhanced data-driven model predictive control for optimizing HVAC energy consumption, indoor air quality and thermal comfort10.1016/j.apenergy.2025.125341 ↗
58. Energy-efficient heating control for nearly zero energy residential buildings with deep reinforcement learning10.1016/j.energy.2022.126209 ↗
59. Solar chimney combined with active cooling systems for enhanced indoor comfort and energy efficiency under extreme climates: A data-driven optimization approach10.1016/j.solener.2025.113809 ↗
60. Aghili, S.A., Rezaei, A.H.M., Tafazzoli, M., Khanzadi, M., and Rahbar, M. (2025). Artificial intelligence approaches to energy management in HVAC systems: A systematic review. Buildings, 15.10.3390/buildings15071008 ↗
61. Adopting occupancy-based HVAC controls in commercial building energy codes: Analysis of cost-effectiveness and decarbonization potential10.1016/j.apenergy.2023.121594 ↗
62. Lessons learned from field demonstrations of model predictive control and reinforcement learning for residential and commercial HVAC: A review10.1016/j.apenergy.2025.126459 ↗
63. Advancing energy efficiency: Innovative technologies and strategic measures for achieving net zero emissions10.20517/cf.2024.48 ↗
64. Occupancy-based HVAC control using deep learning algorithms for estimating online preconditioning time in residential buildings10.1016/j.enbuild.2021.111377 ↗
65. Domain adaptation deep learning and its T-S diagnosis networks for the cross-control and cross-condition scenarios in data center HVAC systems10.1016/j.energy.2023.128084 ↗
66. Energy performance evaluation of the ASHRAE guideline 36 control and reinforcement learning-based control using field measurements10.1016/j.enbuild.2024.115005 ↗
67. Application of an AI-based optimal control framework in smart buildings using borehole thermal energy storage combined with wastewater heat recovery10.1016/j.est.2024.113824 ↗
68. Long-term experimental evaluation and comparison of advanced controls for HVAC systems10.1016/j.apenergy.2024.123706 ↗
69. Modelling building HVAC control strategies using a deep reinforcement learning approach10.1016/j.enbuild.2024.114065 ↗
70. Optimizing energy efficiency, thermal comfort, and indoor air quality in HVAC systems using a robust DRL algorithm10.1016/j.jobe.2024.111493 ↗
71. AI-enhanced automation of building energy optimization using a hybrid stacked model and genetic algorithms: Experiments with seven machine learning techniques and a deep neural network10.1016/j.rineng.2025.104994 ↗
72. Improving energy flexibility and PV self-consumption for a tropical net zero energy office buildings10.1016/j.enbuild.2022.112606 ↗
73. Modeling and energy dynamic control for a ZEH via hybrid model-based deep reinforcement learning10.1016/j.energy.2023.127627 ↗
74. How combination of control methods and renewable energies leads a large commercial building to a zero-emission zone—A case study in U.S10.1016/j.energy.2022.125944 ↗
75. Predictive control optimization of household energy storage devices for load regulation and energy conservation10.1016/j.jobe.2024.111370 ↗
76. Machine learning for optimal net-zero energy consumption in smart buildings
77. Development, investigation and graywolf algorithm-assisted tri-objective optimization of a hybrid renewable-driven HVAC/power system10.1016/j.jobe.2025.111915 ↗
78. Ensemble surrogate modeling of a real-time HVAC set-point optimization framework for PV self-consumption maximization10.1016/j.enbuild.2025.115478 ↗
79. An efficient artificial intelligence energy management system for urban building integrating photovoltaic and storage10.1109/ACCESS.2023.3247636 ↗
80. Li, Y., Antwi-Afari, M.F., Anwer, S., Mehmood, I., Umer, W., Mohandes, S.R., Wuni, I.Y., Abdul-Rahman, M., and Li, H. (2024). Artificial intelligence in net-zero carbon emissions for sustainable building projects: A systematic literature and science mapping review. Buildings, 14.10.3390/buildings14092752 ↗
81. Hua, K., Xu, Q., Li, S., and Fang, L. (2025). Data-driven optimal dispatch of integrated energy in zero-carbon building system considering occupant comfort and uncertainty. Appl. Sci., 15.10.3390/app15084408 ↗
82. An agent-based distributed real-time optimal control strategy for building HVAC systems for applications in the context of future IoT-based smart sensor networks10.1016/j.apenergy.2020.115322 ↗
83. An event-driven multi-agent based distributed optimal control strategy for HVAC systems in IoT-enabled smart buildings10.1016/j.autcon.2021.103919 ↗
84. Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning10.1016/j.apenergy.2023.120936 ↗
85. IoT-based intelligent energy management system for optimal planning of HVAC devices in net-zero emissions PV-battery building considering demand compliance10.1016/j.enconman.2023.117369 ↗
86. Defending against cyber-attacks in building HVAC systems through energy performance evaluation using a physics-informed dynamic Bayesian network (PIDBN)10.1016/j.energy.2025.135369 ↗
87. Investigating the performance of AI-driven smart building systems through advanced deep learning model analysis10.1016/j.egyr.2025.05.003 ↗
88. Connecting the indispensable roles of IoT and artificial intelligence in smart cities: A survey
89. IoT driven building automation systems: A review on energy efficiency, occupant comfort, and sustainability10.1016/j.jobe.2025.112347 ↗
90. IoT-based smart energy management for solar vanadium redox flow battery powered switchable building glazing satisfying the HVAC system of EV charging stations10.1016/j.enconman.2023.116851 ↗
91. Green IoT for energy efficiency: Enabling technologies, and challenges, and future research directions10.1016/j.tsep.2025.103592 ↗
92. A review on enhancing energy efficiency and adaptability through system integration for smart buildings10.1016/j.jobe.2024.109354 ↗
93. Data-driven based HVAC optimization approaches: A systematic literature review10.1016/j.jobe.2021.103678 ↗
94. Human-building interaction for indoor environmental control: Evolution of technology and future prospects10.1016/j.autcon.2023.104938 ↗
95. Michailidis, P., Michailidis, I., Vamvakas, D., and Kosmatopoulos, E. (2023). Model-free HVAC control in buildings: A review. Energies, 16.10.3390/en16207124 ↗
96. Smart design and control of thermal energy storage in low-temperature heating and high-temperature cooling systems: A comprehensive review10.1016/j.rser.2022.112625 ↗
97. Modeling and evaluation of cyber-attacks on grid-interactive efficient buildings10.1016/j.apenergy.2021.117639 ↗
98. Leveraging operational technology and the internet of things to attack smart buildings10.1007/s11416-020-00358-8 ↗
99. Priyadarshini, I. (2024). Anomaly detection of IoT cyberattacks in smart cities using federated learning and split learning. Big Data Cogn. Comput., 8.10.3390/bdcc8030021 ↗
100. A review of scalable and privacy-preserving multi-agent frameworks for distributed energy resources10.1016/j.adapen.2024.100205 ↗