Heating Control Strategy Based on Dynamic Programming for Building Energy Saving and Emission Reduction

Abstract

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.

Advancing Sustainable Building Practices: Intelligent Methods for Enhancing Heating and Cooling Energy Efficiency

“…The study carried out by Ref. [27] focused on achieving building energy savings and emission reduction through a dynamic programming algorithm. The dynamic programming algorithm achieved an impressive 35.1% reduction in energy consumption and emissions against the baseline scenario with a room temperature set at 20 • C. This indicates that the proposed control algorithm surpassed the baseline scenario significantly in terms of energy efficiency.…”

“…Control methods for building heating and cooling systems have been extensively studied, and conventional PID controllers face inefficiency and overshoot issues in energyefficient buildings with slow thermal dynamics [24]. Researchers have looked at datadriven techniques like deep reinforcement learning, model-based techniques like MPC, and optimum control to address the drawbacks of traditional controllers like PID [26][27][28][29][30]. MPC originated in the late 1970s [31,32], integrates a dynamic plant model within the control algorithm, that enables the controller to minimize a cost function and predict the future behavior of the plant.…”