Abstract
The indoor environment of buildings is complex and changeable, and it is difficult to ensure that the indoor humidity is uniform and stable while employing a centralized humidity control system. To address this challenge, this paper proposes an intelligent distributed humidity control system based on model-free deep reinforcement learning. The proposed system consists of three parts: an intelligent controller, distributed facilities, and distributed sensors. The distributed sensors are used to monitor the environmental parameters. This study developed a reinforcement learning algorithm called RH-rainbow and deployed it in distributed facilities. In RH-rainbow, the reward consists of the mean absolute difference of humidity and the energy consumption of distributed facilities. The action is the humidity setpoints and fan settings of the constant humidity machines. The performance of RH-rainbow was evaluated and compared to that of other algorithms in two scenarios with different air outlet settings under different sensor numbers, reporting time intervals, and external interference modes. It was found that RH-rainbow is superior to manual strategies, the traditional analog control strategy, DQN, and PID in terms of uniformity, anti-interference ability, and energy consumption.
Similar content being viewed by others
References
AIC Wiki (2020) Accessed 12 May 2020 Environmental guidelines. https://www.conservation-wiki.com/wiki/Environmental_Guidelines
Atkinson JK (2014) Environmental conditions for the safeguarding of collections: a background to the current debate on the control of relative humidity and temperature. Stud Conserv 59(4):205–212. https://doi.org/10.1179/2047058414Y.0000000141
Plenderleith H, Philippot P (1960) Climatologie et conservation dans les musées: sommaire. Museum Int (Edition Francaise) 13(4):201–289. https://doi.org/10.1111/j.1755-5825.1960.tb01558.x
Ahn KU, Park CS (2020) Application of deep q-networks for model-free optimal control balancing between different hvac systems. Sci Technol Built Environ 26(1):61–74. https://doi.org/10.1080/23744731.2019.1680234
Nagarathinam S, Menon V, Vasan A et al (2020) Marco-multi-agent reinforcement learning based control of building hvac systems. In: Proceedings of the eleventh ACM international conference on future energy systems, pp 57–67. https://doi.org/10.1145/3396851.3397694
Zhao Y, Zhao Q, Xia L et al (2013) A unified control framework of hvac system for thermal and acoustic comforts in office building. In: 2013 IEEE international conference on automation science and engineering (CASE). IEEE, pp 416–421. https://doi.org/10.1109/CoASE.2013.6653964
Ding X, Du W, Cerpa A (2019) Octopus: deep reinforcement learning for holistic smart building control. In: Proceedings of the 6th ACM international conference on systems for energy-efficient buildings, cities, and transportation, pp 326–335. https://doi.org/10.1145/3360322.3360857
Wei T, Wang Y, Zhu Q (2017) Deep reinforcement learning for building hvac control. In: Proceedings of the 54th annual design automation conference 2017, pp 1–6. https://doi.org/10.1145/3061639.3062224
Shuang X, Dongyang Z, Zhen L et al (2019) A combined control method of temperature and humidity inside the museum cabinet. In: 2019 11th International conference on measuring technology and mechatronics automation (ICMTMA). IEEE, pp 322–326. https://doi.org/10.1109/ICMTMA.2019.00078
Xianzhe H (2011) Room temperature and humidity monitoring and energy-saving system. In: 2011 6th International conference on computer science & education (ICCSE). IEEE, pp 537–540. https://doi.org/10.1109/ICCSE.2011.6028696
Zhao X, Tang J, Chen D (2009) Research of temperature and humidity decoupling control for central air-conditioning system. In: 2009 International conference on intelligent human-machine systems and cybernetics. IEEE, pp 404–408. https://doi.org/10.1109/IHMSC.2009.224
Liu S, Wang X, Li S (2016) Fuzzy pid controller design of air handling unit for constant temperature and humidity air-conditioning. In: 2016 8th International conference on intelligent human-machine systems and cybernetics (IHMSC). IEEE, pp 410–414. https://doi.org/10.1109/IHMSC.2016.219
Wu Q, Cai W, Shen S et al (2017) Dynamic analysis of an energy efficiency dehumidifier for building applications. In: 2017 12th IEEE conference on industrial electronics and applications (ICIEA). IEEE, pp 2060–2065. https://doi.org/10.1109/ICIEA.2017.8283177
Wang X, Lu J, Yang Q et al (2013) Performance evaluation of packed tower liquid desiccant dehumidifier based on lssvm. In: 2013 10th Ieee international conference on control and automation (Icca). IEEE, pp 987–990. https://doi.org/10.1109/ICCA.2013.6565050
Yuan X, Pan Y, Yang J et al (2019) Study on the application of reinforcement learning in the operation optimization of hvac system. Build Simul 14:75–87. https://doi.org/10.1007/s12273-020-0602-9
Baghaee S, Ulusoy I (2018) User comfort and energy efficiency in hvac systems by q-learning. In: 2018 26th Signal processing and communications applications conference (SIU). IEEE, pp 1–4. https://doi.org/10.1109/SIU.2018.8404287
Chen Y, Norford LK, Samuelson HW et al (2018) Optimal control of hvac and window systems for natural ventilation through reinforcement learning. Energy Build 169:195–205. https://doi.org/10.1016/j.enbuild.2018.03.051
Qiu S, Li Z, Li Z et al (2020) Model-free control method based on reinforcement learning for building cooling water systems: validation by measured data-based simulation. Energy Build 218:110,055. https://doi.org/10.1016/j.enbuild.2020.110055
Faddel S, Tian G, Zhou Q et al (2020) Data driven q-learning for commercial hvac control. In: 2020 SoutheastCon. IEEE, pp 1–6. https://doi.org/10.1016/10.1109/SoutheastCon44009.2020.9249737
Biemann M, Scheller F, Liu X et al (2021) Experimental evaluation of model-free reinforcement learning algorithms for continuous hvac control. Appl Energy 298:117,164. https://doi.org/10.1016/j.apenergy.2021.117164
Du Y, Zandi H, Kotevska O et al (2021) Intelligent multi-zone residential hvac control strategy based on deep reinforcement learning. Appl Energy 281:116,117. https://doi.org/10.1016/j.apenergy.2020.116117
Gao G, Li J, Wen Y (2020) Deepcomfort: energy-efficient thermal comfort control in buildings via reinforcement learning. IEEE Internet Things J 7(9):8472–8484. https://doi.org/10.1109/JIOT.2020.2992117
Valladares W, Galindo M, Gutiérrez J et al (2019) Energy optimization associated with thermal comfort and indoor air control via a deep reinforcement learning algorithm. Build Environ 155:105–117. https://doi.org/10.1016/j.buildenv.2019.03.038
Sakuma Y, Nishi H (2020) Airflow direction control of air conditioners using deep reinforcement learning. In: 2020 SICE international symposium on control systems (SICE ISCS). IEEE, pp 61–68. https://doi.org/10.23919/SICEISCS48470.2020.9083565
Yu L, Sun Y, Xu Z et al (2020) Multi-agent deep reinforcement learning for hvac control in commercial buildings. IEEE Trans Smart Grid 12(1):407–419. https://doi.org/10.1109/TSG.2020.3011739
Xu S, Wang Y, Wang Y et al (2020) One for many: transfer learning for building hvac control. In: Proceedings of the 7th ACM international conference on systems for energy-efficient buildings, cities, and transportation, pp 230–239. https://doi.org/10.1145/3408308.3427617
Zhang Y, Zhou Y, Lu H et al (2021) Cooperative multi-agent actor–critic control of traffic network flow based on edge computing. Futur Gener Comput Syst 123:128–141. https://doi.org/10.1016/j.future.2021.04.018
Shang M, Zhou Y, Fujita H (2021) Deep reinforcement learning with reference system to handle constraints for energy-efficient train control. Inf Sci 570:708–721. https://doi.org/10.1016/j.ins.2021.04.088
Pérez S, Arroba P, Moya JM (2021) Energy-conscious optimization of edge computing through deep reinforcement learning and two-phase immersion cooling. Futur Gener Comput Syst 125:891–907. https://doi.org/10.1016/j.future.2021.07.031
Deng X, Zhang Y, Zhang Y et al (2022) Towards optimal hvac control in non-stationary building environments combining active change detection and deep reinforcement learning. Build Environ 211:108,680. https://doi.org/10.1016/j.buildenv.2021.108680
Tsenis TT, Kapsimanis G, Kappatos V (2021) Smartclima: reinforcement learning residential thermostat-less heating control system. In: 2021 International conference on electrical, computer, communications and mechatronics engineering (ICECCME), pp 1–6. https://doi.org/10.1109/ICECCME52200.2021.9591000
Ferdyn-Grygierek J, Grygierek K (2019) Hvac control methods for drastically improved hygrothermal museum microclimates in warm season. Build Environ 149:90–99. https://doi.org/10.1016/j.buildenv.2018.12.018
Hessel M, Modayil J, Van Hasselt H et al (2017) Rainbow: combining improvements in deep reinforcement learning. arXiv:1710.02298
Gupta A, Badr Y, Negahban A et al (2021) Energy-efficient heating control for smart buildings with deep reinforcement learning. J Build Eng 34:101,739. https://doi.org/10.1016/j.jobe.2020.101739
Schaul T, Quan J, Antonoglou I et al (2015) Prioritized experience replay. Comput Sci
Lillicrap TP, Hunt JJ, Pritzel A et al (2015) Continuous control with deep reinforcement learning. arXiv:1509.02971
Rockafellar RT (2015) Convex analysis. Princeton University Press. https://doi.org/10.1515/9781400873173
Enriko IKA, Putra RA, Estananto (2021) Automatic temperature control system on smart poultry farm using pid method. Green Intell Syst Appl 1(1):37–43. https://doi.org/10.53623/gisa.v1i1.40
Acknowledgements
The authors would like to thank the reviewers for their detailed reviews and constructive comments, which have helped improve the quality of this paper. And thank professor Zhu of Dalian University of Technology for providing simulation support. This work is supported by National Key R&D Program of China under Grant No. 2020YFC1522503.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Guo, D., Luo, D., Zhang, Y. et al. Application of deep reinforcement learning to intelligent distributed humidity control system. Appl Intell 53, 16724–16746 (2023). https://doi.org/10.1007/s10489-022-04320-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04320-7