Affiliations: [a] Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China | [b] Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China | [c] Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China
Correspondence:
[*]
Corresponding author: Jianping Chen, Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China. E-mail: [email protected].
Abstract: In the field of building equipment control, the traditional methods have some problems – instability and slow convergence. To deal with these problems, a new Sarsa-based adaptive controller, SAC (Sarsa-based adaptive controller) was proposed. Based on the model of the exchange mechanism about the building energy consumption, the proposed method with Sarsa algorithm models the exchange mechanism of the building energy consumption, and tries to find the best control policy, which can decrease the energy consumption without losing the performance of good comfort of the building occupants. Compared with the PID method, the proposed SAC has better convergence performance and robustness.
Keywords: Energy conservation, Reinforcement learning, Sarsa algorithm, adaptive controller
