Abstract
In this paper, we apply reinforcement learning to the power management control of building multi-type air-conditioners. In general, reinforcement learning requires several tens of thousands of training episodes before the control performance reaches a practical level. Therefore, applying it directly to air-conditioning control in 10-min intervals would require unrealistic training days as several years. We attempted to shorten the learning period by learning in advance on a virtual building that emulates the dynamic characteristics of an actual building. Since it is difficult to create exactly the same air-conditioning environment of the actual building, we propose a method to select the closest one from several virtual buildings based on the differences of immediate reward.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Council of Australian Governments (COAG) National Strategy on Energy Efficiency: Best Practice Maintenance & Operation of HVAC Systems for Energy Efficiency and Resources, pp. 1–88 (2012)
Yu, L., Qin, S., Zhang, M., Shen, C., Jiang, T., Guan, X.: A review of deep reinforcement learning for smart building energy management. IEEE Internet Things J. 8(15), 12046–12063 (2021)
Han, Y., Kim, W.: Development and validation of building control algorithm energy management. Buildings 11(131), 1–33 (2021)
Aoki, Y., Ito, H., Ninagawa, C., Morikawa, J.: Smart grid real-time pricing optimization control with simulated annealing algorithm for office building air-conditioning facilities. In: IEEE International Conference on Industry Technology, Lyon, France, pp. 1309–1313 (2018)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
Pan, J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Goetzler, W.: Variable refrigerant flow systems. ASHRAE J. (2007)
Watkins, C.J.C.H., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8, 279–292 (1992)
Matsukawa, S., Ninagawa, C., Morikawa, J., Inaba, T., Kondo, S.: Stable segment method for multiple linear regression on baseline estimation for smart grid fast automated demand response. In: IEEE Innovative Smart Grid Technologies ISGT-Asia, Chengdu, China, pp. 2571–2576 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Aoki, Y., Goto, S., Takahashi, Y., Ninagawa, C., Morikawa, J. (2022). Multi-track Transfer Reinforcement Learning for Power Consumption Management of Building Multi-type Air-Conditioners. In: Iliadis, L., Jayne, C., Tefas, A., Pimenidis, E. (eds) Engineering Applications of Neural Networks. EANN 2022. Communications in Computer and Information Science, vol 1600. Springer, Cham. https://doi.org/10.1007/978-3-031-08223-8_33
Download citation
DOI: https://doi.org/10.1007/978-3-031-08223-8_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08222-1
Online ISBN: 978-3-031-08223-8
eBook Packages: Computer ScienceComputer Science (R0)