Optimization of thermal comfort, indoor quality, and energy-saving in campus classroom through deep Q learning

• Published in: Case studies in thermal engineering 2021-04, Vol.24, p.100842, Article 100842
• Main Authors: Yu, Kuan-Heng, Chen, Yi-An, Jaimes, Emanuel, Wu, Wu-Chieh, Liao, Kuo-Kai, Liao, Jen-Chung, Lu, Kuang-Chin, Sheu, Wen-Jenn, Wang, Chi-Chuan
• Format: Article
• Language: English
• Subjects: Deep Q-Learning; Energy saving; Indoor air quality; Reinforcement learning; Thermal comfort
• ISSN: 2214-157X; 2214-157X
• DOI: 10.1016/j.csite.2021.100842

This study develops a control algorithm for optimization the energy consumptions of air-conditioning and exhaust fans through Deep Q-Learning in reinforcement learning. The proposed agent is able to balance indoor air quality (CO2), thermal comfort, and energy consumption. The algorithm was first trained in a similar environment simulation, and was then applied and tested in a classroom with maximum 72 occupants. Tests were conducted in one month during summer. The effects of outdoor environments and class conditions on the energy-saving and indoor air quality are examined in details. Via agent control, optimization of indoor air quality, thermal comfort, and energy consumption of air-conditioning units and exhaust fans can be achieved. With the same thermal comfort, the agent can offer energy-saving up to 43% when compared to air-conditioning with a fixed temperature of 25 °C, and on average the agent offers about 19% less of the energy consumption. Yet the corresponding CO2 level is reduced by about 24% with the agent control. Similarly, when compared with a fixed temperature of 26 °C, the agent can offer about 15% lower energy consumption on average and the concentration of carbon dioxide can be reduced by 13% in average.