Demonstration and Analysis of Reinforcement Learning-Based Building Autonomous Control for a Large Retail Facility in Cooling Season

Juno Lee; Jun-Sub Kim; Seong-Woo Park; Hyeun Jun Moon

doi:10.21086/ksles.2026.8.33.4.405

All Issue

2026 Vol.33, Issue 4 Preview Page Next Page

Research Article

Demonstration and Analysis of Reinforcement Learning-Based Building Autonomous Control for a Large Retail Facility in Cooling Season 심층강화학습 기반의 건물 자율운전 모델 개발 및 대형 판매시설 대상 냉방기 실증

31 August 2026. pp. 405-416

PDF XML

Abstract

This study evaluated the field performance of an artificial intelligence-based autonomous building control (aiBAC) model in a large retail building during the summer season. The control model was developed using reinforcement learning and pre-trained in a hybrid simulation environment to ensure stable operation under real building conditions. A total of 50 valid operating days were analyzed, including 29 days under conventional control and 21 days under autonomous control. Energy performance was assessed using gas consumption, while thermal comfort performance was evaluated using the thermal compliance ratio and mean out-of-band intensity. The results showed that the autonomous control reduced daily gas consumption by 9.2% compared with conventional control. In addition, the temperature compliance ratio improved from 51.4% to 74.6%, while the mean out-of-band intensity decreased from 0.82°C to 0.55°C, indicating improved thermal comfort and more stable indoor temperature control. Further analysis under different outdoor temperature and occupancy conditions confirmed consistent energy-saving performance. These findings demonstrate that reinforcement learning-based autonomous control can simultaneously improve energy efficiency and thermal comfort in real-world retail buildings and has strong potential for practical application in intelligent building energy management.

Keywords

Deep Reinforcement Learning

Building Autonomous Control

Retail Facility

Thermal comfort

Energy Reduction

References

Agouzoul, A., Simeu, E., & Tabaa, M. (2024). Advancing sustainable building practices: intelligent methods for enhancing heating and cooling energy efficiency. Sustainability, 16(7), 2879. https://doi.org/10.3390/su16072879

10.3390/su16072879

ASHRAE (2024). 2024 ASHRAE handbook: Heating, ventilating, and air-conditioning systems and equipment (SI ed.). Peachtree Corners, GA: Author.

Choi, Y. J., Choi, E. J., Byun, J. Y., Moon, H. J., Sung, M. K., & Moon, J. W. (2025). CO₂ - and PM_2.5-focused optimal ventilation strategy based on predictive control. Indoor Air, 2025, Article 6652442. https://doi.org/10.1155/ina/6652442

10.1155/ina/6652442

Fan, Y., Fu, Q., Chen, J., Wang, Y., Lu, Y., & Liu, K. (2025). A deep reinforcement learning control method for multi-zone precooling in commercial buildings. Applied Thermal Engineering, 260, Article 124987. https://doi.org/10.1016/j.applthermaleng.2024.124987

10.1016/j.applthermaleng.2024.124987

González-Torres, M., Pérez-Lombard, L., Coronel, J. F., Maestre, I. R., & Yan, D. (2022). A review on buildings energy information: Trends, end-uses, fuels and drivers. Energy Reports, 8, 626-637. https://doi.org/10.1016/j.egyr.2021.11.280

10.1016/j.egyr.2021.11.280

Guo, F., Ham, S. W., Kim, D., Kim, S. H., & Moon, H. J. (2025a). Designing reinforcement learning algorithms for building HVAC control: From experimental observation to simulation comparisons. Applied Thermal Engineering, 270, Article 126106. https://doi.org/10.1016/j.applthermaleng.2025.126106

10.1016/j.applthermaleng.2025.126106

Guo, F., Ham, S. W., Kim, D., & Moon, H. J. (2025b). Deep reinforcement learning control for co-optimizing energy consumption, thermal comfort, and indoor air quality in an office building. Applied Energy, 377(Part A), Article 124467. https://doi.org/10.1016/j.apenergy.2024.124467

10.1016/j.apenergy.2024.124467

Kim, J. S., & Moon, H. J. (2023). Real-time thermal comfort classification using an occupants activity model from thermal images. Proceedings of Building Simulation 2023: 18^th Conference of IBPSA, 141-147. https://doi.org/10.26868/25222708.2023.1223

10.26868/25222708.2023.1223

Kim, S. H., & Moon, H. J. (2026). Reinforcement learning–based building control considering decision-makers’ preferences between energy use and indoor environmental quality. Indoor Air, 2026, Article 4881534. https://doi.org/10.1155/ina/4881534

10.1155/ina/4881534

Kolokotroni, M., Mylona, Z., Evans, J., Foster, A., & Liddiard, R. (2019). Supermarket energy use in the UK. Energy Procedia, 161, 325-332.

10.1016/j.egypro.2019.02.108

Lei, Y., Zhan, S., Ono, E., Peng, Y., Zhang, Z., Hasama, T., & Chong, A. (2022). A practical deep reinforcement learning framework for multivariate occupant-centric control in buildings. Applied Energy, 324, 119742. https://doi.org/10.1016/j.apenergy.2022.119742

10.1016/j.apenergy.2022.119742

Nagy, Z., Henze, G., Dey, S., Arroyo, J., Helsen, L., Zhang, X., et al. (2023). Ten questions concerning reinforcement learning for building energy management. Building and Environment, 241, Article 110435. https://doi.org/10.1016/j.buildenv.2023.110435

10.1016/j.buildenv.2023.110435

Wang, S.-W., Cheng, J.-H., & Zhang, C.-L. (2025). Enhancing dedicated outdoor air system heating performance in cold climates with integrated enthalpy heat exchanger and heat pump. Energy and Buildings, 352, 116052. https://doi.org/10.1016/j.enbuild.2025.116052

10.1016/j.enbuild.2025.116052

Wang, Z., & Hong, T. (2020). Reinforcement learning for building controls: The opportunities and challenges. Applied Energy, 269, 115036. https://doi.org/10.1016/j.apenergy.2020.115036

10.1016/j.apenergy.2020.115036

Shaikh, P. H., Nor, N. B. M., Nallagownden, P., Elamvazuthi, I., & Ibrahim, T. (2014). A review on optimized control systems for building energy and comfort management of smart sustainable buildings. Renewable and Sustainable Energy Reviews, 34, 409-429. https://doi.org/10.1016/j.rser.2014.03.027

10.1016/j.rser.2014.03.027

Silva, A. S., Ghisi, E., & Lamberts, R. (2016). Performance evaluation of long-term thermal comfort indices in building simulation according to ASHRAE Standard 55. Building and Environment, 102, 95-115. https://doi.org/10.1016/j.buildenv.2016.03.004

10.1016/j.buildenv.2016.03.004

Yoo, J., Eom, J., & Zhou, Y. (2024). Thermal comfort and retail sales: A big data analysis of extreme temperature’s impact on brick-and-mortar stores. Journal of Retailing and Consumer Services, 77, 103699. https://doi.org/10.1016/j.jretconser.2023.103699

10.1016/j.jretconser.2023.103699

Yu, L., Sun, Y., Xu, Z., Shen, C., Yue, D., & Jiang, T. (2021a). Multi-agent deep reinforcement learning for HVAC control in commercial buildings. IEEE Transactions on Smart Grid, 12(1), 407-419. https://doi.org/10.1109/TSG.2020.3011739

10.1109/TSG.2020.3011739

Yu, L., Qin, S., Zhang, M., Shen, C., Jiang, T., & Guan, X. (2021b). A review of deep reinforcement learning for smart building energy management. IEEE Internet of Things Journal, 8(15), 12046-12063. https://doi.org/10.1109/JIOT.2021.3078462

10.1109/JIOT.2021.3078462

Information

Publisher :The Korean Society of Living Environmental System
Publisher(Ko) :한국생활환경학회
Journal Title :Journal of The Korean Society of Living Environmental System
Journal Title(Ko) :한국생활환경학회
Volume : 33
No :4
Pages :405-416
Received Date : 2026-06-28
Revised Date : 2026-07-08
Accepted Date : 2026-07-09
DOI :https://doi.org/10.21086/ksles.2026.8.33.4.405

Journal of The Korean Society of Living Environmental System ISSN:1226-1289(Print) 한국생활환경학회

All Issue