Heating, ventilation, and air conditioning (HVAC) systems are a major contributor to global building energy consumption; however, their control is complicated by inherent parametric uncertainties and time-varying disturbances. To address the limitations of conventional methods, a novel two-stage "learning-and-reusing" framework was proposed, which fundamentally differs from existing methods by: (i) decoupling parameter learning from disturbance rejection to avoid the single-stage trade-off; (ii) using concurrent learning and an estimator for parameter identification under relaxed excitation conditions and input saturation. In the first learning stage, a concurrent-learning-based adaptive controller accurately identifies key thermodynamic parameters, such as the heat transfer coefficient and the cross-sectional areas of the wall, while simultaneously maintaining precise temperature regulation, thereby building a reliable knowledge base. In the second reusing stage, the identified model is used within a disturbance observer-based robust controller to precisely compensate for time-varying disturbances, such as fluctuating solar radiation and internal heat loads. Simulations on multi-zone building models validated the framework, demonstrating successful parameter convergence and superior robust tracking performance compared to conventional methods. This work offers an efficient, bio-inspired solution for intelligent building thermal management.
Citation: Suna Wang, Zhaohui Qi, Haiqun Chen, Lu Sun, Haotian Shi. A bio-inspired learning-and-reusing control strategy for multi-zone HVAC systems[J]. Electronic Research Archive, 2026, 34(4): 2194-2221. doi: 10.3934/era.2026099
Heating, ventilation, and air conditioning (HVAC) systems are a major contributor to global building energy consumption; however, their control is complicated by inherent parametric uncertainties and time-varying disturbances. To address the limitations of conventional methods, a novel two-stage "learning-and-reusing" framework was proposed, which fundamentally differs from existing methods by: (i) decoupling parameter learning from disturbance rejection to avoid the single-stage trade-off; (ii) using concurrent learning and an estimator for parameter identification under relaxed excitation conditions and input saturation. In the first learning stage, a concurrent-learning-based adaptive controller accurately identifies key thermodynamic parameters, such as the heat transfer coefficient and the cross-sectional areas of the wall, while simultaneously maintaining precise temperature regulation, thereby building a reliable knowledge base. In the second reusing stage, the identified model is used within a disturbance observer-based robust controller to precisely compensate for time-varying disturbances, such as fluctuating solar radiation and internal heat loads. Simulations on multi-zone building models validated the framework, demonstrating successful parameter convergence and superior robust tracking performance compared to conventional methods. This work offers an efficient, bio-inspired solution for intelligent building thermal management.
| [1] |
N. Asim, M. Badiei, M. Mohammad, H. Razali, A. Rajabi, L. C. Haw, et al., Sustainability of heating, ventilation and air-conditioning (HVAC) systems in buildings-An overview, Int. J. Environ. Res. Public Health, 19 (2022), 1016. https://doi.org/10.3390/ijerph19021016 doi: 10.3390/ijerph19021016
|
| [2] |
X. Wang, Y. Bai, Z. Li, W. Zhao, S. Ding, Observer-based event triggering security load frequency control for power systems involving air conditioning loads, Electron. Res. Arch., 32 (2024), 6258–6275. https://doi.org/10.3934/era.2024291 doi: 10.3934/era.2024291
|
| [3] |
S. Sierla, H. Ihasalo, V. Vyatkin, A review of reinforcement learning applications to control of heating, ventilation and air conditioning systems, Energies, 15 (2022), 3526. https://doi.org/10.3390/en15103526 doi: 10.3390/en15103526
|
| [4] |
S. Taheri, P. Hosseini, A. Razban, Model predictive control of heating, ventilation, and air conditioning (HVAC) systems: A state-of-the-art review, J. Build. Eng., 60 (2022), 105067. https://doi.org/10.1016/j.jobe.2022.105067 doi: 10.1016/j.jobe.2022.105067
|
| [5] |
A. Afram, F. Janabi-Sharifi, Theory and applications of HVAC control systems-A review of model predictive control (MPC), Build. Environ., 72 (2014), 343–355. https://doi.org/10.1016/j.buildenv.2013.11.016 doi: 10.1016/j.buildenv.2013.11.016
|
| [6] |
G. Serale, M. Fiorentini, A. Capozzoli, D. Bernardini, A. Bemporad, Model predictive control (MPC) for enhancing building and HVAC system energy efficiency: Problem formulation, applications and opportunities, Energies, 11 (2018), 631. https://doi.org/10.3390/en11030631 doi: 10.3390/en11030631
|
| [7] |
B. Tashtoush, M. Molhim, M. Al-Rousan, Dynamic model of an HVAC system for control analysis, Energy, 30 (2005), 1729–1745. https://doi.org/10.1016/j.energy.2004.10.004 doi: 10.1016/j.energy.2004.10.004
|
| [8] |
H. Zhao, H. Cui, Y. Zhao, X. Dai, A neural network-based adaptive fault-tolerant cooperation control for multiple trains with unknown parameters, Electron. Res. Arch., 33 (2025), 3931–3949. https://doi.org/10.3934/era.2025174 doi: 10.3934/era.2025174
|
| [9] |
Q. Zhang, M. Mu, H. Ji, Q. Wang, X. Wang, An adaptive type-2 fuzzy sliding mode tracking controller for a robotic manipulator, Electron. Res. Arch., 31 (2023), 3791–3813. https://doi.org/10.3934/era.2023193 doi: 10.3934/era.2023193
|
| [10] |
M. Shen, T. Zhang, J. H. Park, Q. G. Wang, L. W. Li, Iterative proportional-integral interval estimation of linear discrete-time systems, IEEE Trans. Autom. Control, 68 (2023), 4249–4256. https://doi.org/10.1109/TAC.2022.3203226 doi: 10.1109/TAC.2022.3203226
|
| [11] |
P. Michailidis, I. Michailidis, D. Vamvakas, E. Kosmatopoulos, Model-free HVAC control in buildings: A review, Energies, 16 (2023), 7124. https://doi.org/10.3390/en16207124 doi: 10.3390/en16207124
|
| [12] |
X. Wang, B. Dong, Long-term experimental evaluation and comparison of advanced controls for HVAC systems, Appl. Energy, 371 (2024), 123706. https://doi.org/10.1016/j.apenergy.2024.123706 doi: 10.1016/j.apenergy.2024.123706
|
| [13] |
X. Xin, Z. Zhang, Y. Zhou, Y. Liu, D. Wang, S. Nan, A comprehensive review of predictive control strategies in heating, ventilation, and air-conditioning (HVAC): Model-free VS model, J. Build. Eng., 94 (2024), 110013. https://doi.org/10.1016/j.jobe.2024.110013 doi: 10.1016/j.jobe.2024.110013
|
| [14] |
M. A. Adesanya, H. Obasekore, A. Rabiu, W. H. Na, Q. O. Ogunlowo, T. D. Akpenpuun, et al., Deep reinforcement learning for PID parameter tuning in greenhouse HVAC system energy optimization: A TRNSYS-Python cosimulation approach, Expert Syst. Appl., 252 (2024), 124126. https://doi.org/10.1016/j.eswa.2024.124126 doi: 10.1016/j.eswa.2024.124126
|
| [15] |
Y. E. Jang, Y. J. Kim, J. P. S. Catalão, Optimal HVAC system operation using online learning of interconnected neural networks, IEEE Trans. Smart Grid, 12 (2021), 3030–3042. https://doi.org/10.1109/TSG.2021.3051564 doi: 10.1109/TSG.2021.3051564
|
| [16] |
J. Cho, Y. Heo, J. W. Moon, An intelligent HVAC control strategy for supplying comfortable and energy-efficient school environment, Adv. Eng. Inf., 55 (2023), 101895. https://doi.org/10.1016/j.aei.2023.101895 doi: 10.1016/j.aei.2023.101895
|
| [17] |
H. Wang, S. Wang, A disturbance compensation enhanced control strategy of HVAC systems for improved building indoor environment control when providing power grid frequency regulation, Renewable Energy, 169 (2021), 1330–1342. https://doi.org/10.1016/j.renene.2021.01.102 doi: 10.1016/j.renene.2021.01.102
|
| [18] |
T. Yu, Z. Zhang, Y. Li, W. Zhao, J. Zhang, Improved active disturbance rejection controller for rotor system of magnetic levitation turbomachinery, Electron. Res. Arch., 31 (2023), 1570–1586. https://doi.org/10.3934/era.2023080 doi: 10.3934/era.2023080
|
| [19] |
M. Shen, X. Wang, J. H. Park, Y. Yi, W. W. Che, Extended disturbance-observer-based data-driven control of networked nonlinear systems with event-triggered output, IEEE Trans. Syst. Man Cybern. Syst., 53 (2023), 3129–3140. https://doi.org/10.1109/TSMC.2022.3222491 doi: 10.1109/TSMC.2022.3222491
|
| [20] |
S. A. A. Rizvi, A. J. Pertzborn, Z. Lin, Reinforcement learning based optimal tracking control under unmeasurable disturbances with application to HVAC systems, IEEE Trans. Neural Networks Learn. Syst., 33 (2022), 7523–7533. https://doi.org/10.1109/TNNLS.2021.3085358 doi: 10.1109/TNNLS.2021.3085358
|
| [21] |
N. Nassif, A robust $CO_{2}$-based demand-controlled ventilation control strategy for multi-zone HVAC systems, Energy Build., 45 (2012), 72–81. https://doi.org/10.1016/j.enbuild.2011.10.018 doi: 10.1016/j.enbuild.2011.10.018
|
| [22] |
Y. Zeng, Z. Zhang, A. Kusiak, Predictive modeling and optimization of a multi-zone HVAC system with data mining and firefly algorithms, Energy, 86 (2015), 393–402. https://doi.org/10.1016/j.energy.2015.04.045 doi: 10.1016/j.energy.2015.04.045
|
| [23] |
Y. J. Kim, A supervised-learning-based strategy for optimal demand response of an HVAC system in a multi-zone office building, IEEE Trans. Smart Grid, 11 (2020), 4212–4226. https://doi.org/10.1109/TSG.2020.2986539 doi: 10.1109/TSG.2020.2986539
|
| [24] |
S. He, S. L. Dai, Z. Zhao, T. Zou, Y. Ma, UDE-based distributed formation control for MSVs with collision avoidance and connectivity preservation, IEEE Trans. Ind. Inf., 20 (2024), 1476–1487. https://doi.org/10.1109/TII.2023.3274234 doi: 10.1109/TII.2023.3274234
|
| [25] |
G. Lymperopoulos, P. Ioannou, Building temperature regulation in a multi-zone HVAC system using distributed adaptive control, Energy Build., 215 (2020), 109825. https://doi.org/10.1016/j.enbuild.2020.109825 doi: 10.1016/j.enbuild.2020.109825
|
| [26] |
S. Ma, Y. Zou, S. Li, Coordinated control for air handling unit and variable air volume boxes in multi-zone HVAC system, J. Process Control, 107 (2021), 17–26. https://doi.org/10.1016/j.jprocont.2021.09.008 doi: 10.1016/j.jprocont.2021.09.008
|
| [27] |
C. Cui, J. Xue, L. Liu, Optimal control of HVAC systems through active disturbance rejection control-assisted reinforcement learning, Energy, 323 (2025), 135824. https://doi.org/10.1016/j.energy.2025.135824 doi: 10.1016/j.energy.2025.135824
|
| [28] |
J. Mei, X. Xia, Distributed control for a multi-evaporator air conditioning system, Control Eng. Pract., 90 (2019), 85–100. https://doi.org/10.1016/j.conengprac.2019.06.017 doi: 10.1016/j.conengprac.2019.06.017
|
| [29] |
G. Chen, H. Zhang, H. Hui, Y. Song, Fast Wasserstein-distance-based distributionally robust chance-constrained power dispatch for multi-zone HVAC systems, IEEE Trans. Smart Grid, 12 (2021), 4016–4028. https://doi.org/10.1109/TSG.2021.3076237 doi: 10.1109/TSG.2021.3076237
|
| [30] |
Q. Jing, Y. Guo, Y. Liu, Y. Wang, C. Du, X. Liu, Optimization study of energy saving control strategy of carbon dioxide heat pump water heater system under the perspective of energy storage, Appl. Therm. Eng., 283 (2025), 129030. https://doi.org/10.1016/j.applthermaleng.2025.129030 doi: 10.1016/j.applthermaleng.2025.129030
|
| [31] |
Y. Liu, C. Cui, A bi-level real-time optimal control strategy for thermal coupled multi-zone dedicated outside air system-assisted HVAC systems, Energy, 306 (2024), 132343. https://doi.org/10.1016/j.energy.2024.132343 doi: 10.1016/j.energy.2024.132343
|
| [32] |
J. Mei, Z. Lu, J. Hu, Y. Fan, Energy-efficient optimal guaranteed cost intermittent-switch control of a direct expansion air conditioning system, IEEE/CAA J. Autom. Sin., 8 (2021), 1852–1866. https://doi.org/10.1109/JAS.2020.1003447 doi: 10.1109/JAS.2020.1003447
|
| [33] |
H. Zhang, L. Cai, Decentralized nonlinear adaptive control of an HVAC system, IEEE Trans. Syst. Man Cybern. Part C Appl. Rev., 32 (2002), 493–498. https://doi.org/10.1109/TSMCC.2002.807271 doi: 10.1109/TSMCC.2002.807271
|
| [34] |
A. Adegbenro, M. Short, C. Angione, An integrated approach to adaptive control and supervisory optimisation of HVAC control systems for demand response applications, Energies, 14 (2021), 2078. https://doi.org/10.3390/en14082078 doi: 10.3390/en14082078
|
| [35] |
M. A. Abuhussain, B. S. Alotaibi, M. S. Aliero, M. Asif, M. A. Alshenaifi, Y. A. Dodo, Adaptive HVAC system based on fuzzy controller approach, Appl. Sci., 13 (2023), 11354. https://doi.org/10.3390/app132011354 doi: 10.3390/app132011354
|
| [36] | C. Wang, D. J. Hill, Learning from neural control, IEEE Trans. Neural Networks, 17 (2006), 130–146. https://doi.org/10.1109/TNN.2005.860843 |
| [37] |
Y. Pan, H. Yu, Biomimetic hybrid feedback feedforward neural-network learning control, IEEE Trans. Neural Networks Learn. Syst., 28 (2017), 1481–1487. https://doi.org/10.1109/TNNLS.2016.2527501 doi: 10.1109/TNNLS.2016.2527501
|
| [38] |
R. Kamalapurkar, B. Reish, G. Chowdhary, W. E. Dixon, Concurrent learning for parameter estimation using dynamic state-derivative estimators, IEEE Trans. Autom. Control, 62 (2017), 3594–3601. https://doi.org/10.1109/TAC.2017.2671343 doi: 10.1109/TAC.2017.2671343
|
| [39] |
H. Shi, S. He, S. L. Dai, C. Dong, Cooperative learning from neural formation control for uncertain marine surface vehicles with input saturation under switching topology, IEEE Trans. Transp. Electrif., 10 (2024), 7828–7839. https://doi.org/10.1109/TTE.2024.3400366 doi: 10.1109/TTE.2024.3400366
|
| [40] |
M. Shen, X. Wang, S. Zhu, Z. Wu, T. Huang, Data-driven event-triggered adaptive dynamic programming control for nonlinear systems with input saturation, IEEE Trans. Cybern., 54 (2024), 1178–1188. https://doi.org/10.1109/TCYB.2023.3337779 doi: 10.1109/TCYB.2023.3337779
|
| [41] |
Y. Chen, S. Treado, Development of a simulation platform based on dynamic models for HVAC control analysis, Energy Build., 68 (2014), 376–386. https://doi.org/10.1016/j.enbuild.2013.09.016 doi: 10.1016/j.enbuild.2013.09.016
|
| [42] |
Y. Jiang, S. Zhu, Q. Xu, B. Yang, X. Guan, Hybrid modeling-based temperature and humidity adaptive control for a multi-zone HVAC system, Appl. Energy, 334 (2023), 120622. https://doi.org/10.1016/j.apenergy.2022.120622 doi: 10.1016/j.apenergy.2022.120622
|
Figures(21) / Tables(3)
Suna Wang, Zhaohui Qi, Haiqun Chen, Lu Sun, Haotian Shi. A bio-inspired learning-and-reusing control strategy for multi-zone HVAC systems[J]. Electronic Research Archive, 2026, 34(4): 2194-2221. doi: 10.3934/era.2026099
DownLoad: