Data-driven HVAC Control Using Symbolic Regression: Design and Implementation
This work addresses energy efficiency and comfort in building HVAC systems, representing an incremental improvement over existing methods.
The study tackled HVAC energy management by developing a data-driven control framework using symbolic regression and model predictive control, which reduced peak power by 16.1% compared to a thermostat controller in a real campus building.
The large amount of data collected in buildings makes energy management smarter and more energy efficient. This study proposes a design and implementation methodology of data-driven heating, ventilation, and air conditioning (HVAC) control. Building thermodynamics is modeled using a symbolic regression model (SRM) built from the collected data. Additionally, an HVAC system model is also developed with a data-driven approach. A model predictive control (MPC) based HVAC scheduling is formulated with the developed models to minimize energy consumption and peak power demand and maximize thermal comfort. The performance of the proposed framework is demonstrated in the workspace in the actual campus building. The HVAC system using the proposed framework reduces the peak power by 16.1\% compared to the widely used thermostat controller.