Tianjin Key Laboratory of Clean Energy and Pollutant Control, School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 400301, China.
Institute of Building Environment and Energy, China Academy of Building Research, Beijing 100013, China.
Int J Environ Res Public Health. 2022 Oct 29;19(21):14137. doi: 10.3390/ijerph192114137.
Finding the optimal balance between end-user's comfort, lifestyle preferences and the cost of the heating, ventilation and air conditioning (HVAC) system, which requires intelligent decision making and control. This paper proposes a heating control method for HVAC based on dynamic programming. The method first selects the most suitable modeling approach for the controlled building among three machine learning modeling techniques by means of statistical performance metrics, after which the control of the HVAC system is described as a constrained optimization problem, and the action of the controller is given by solving the optimization problem through dynamic programming. In this paper, the variable 'thermal energy storage in building' is introduced to solve the problem that dynamic programming is difficult to obtain the historical state of the building due to the requirement of no aftereffect, while the room temperature and the remaining start hours of the Primary Air Unit are selected to describe the system state through theoretical analysis and trial and error. The results of the TRNSYS/Python co-simulation show that the proposed method can maintain better indoor thermal environment with less energy consumption compared to carefully reviewed expert rules. Compared with expert rule set 'baseline-20 °C', which keeps the room temperature at the minimum comfort level, the proposed control algorithm can save energy and reduce emissions by 35.1% with acceptable comfort violation.
在满足终端用户舒适度、生活方式偏好和暖通空调 (HVAC) 系统成本之间找到最佳平衡，这需要智能决策和控制。本文提出了一种基于动态规划的 HVAC 加热控制方法。该方法首先通过统计性能指标在三种机器学习建模技术中选择最适合受控建筑物的建模方法，然后将 HVAC 系统的控制描述为约束优化问题，并通过动态规划求解优化问题来给出控制器的作用。在本文中，引入了“建筑物中的热能存储”变量，以解决由于无后效要求，动态规划难以获得建筑物历史状态的问题，而通过理论分析和反复试验，选择房间温度和主要空气单元的剩余启动时间来描述系统状态。TRNSYS/Python 联合仿真的结果表明，与经过精心审查的专家规则相比，所提出的方法可以在消耗较少能源的情况下保持更好的室内热环境。与将室温保持在最低舒适水平的专家规则集“基线-20°C”相比，所提出的控制算法可以在可接受的舒适度违规情况下节省 35.1%的能源并减少排放。
