The Smart Buildings Control Suite: A Diverse Open Source Benchmark to Evaluate and Scale HVAC Control Policies for Sustainability

TL;DR

The paper tackles scaling HVAC optimization by introducing The Smart Buildings Control Suite, an open-source benchmark with real-world data (11 buildings over 6 years), a scalable data-driven simulator, and a PINN-based simulator alternative. It models energy and emissions optimization as an MDP with a multi-objective reward, the 3C Reward, enabling offline RL and MPC approaches while remaining compatible with OpenAI Gym and TensorFlow Datasets. The authors demonstrate a fast, calibratable FD-based simulator and a modular PINN that matches real-world dynamics more efficiently than purely data-driven models, and they show that SAC can surpass a baseline controller in a representative building. Overall, the benchmark aims to accelerate scalable, reproducible HVAC control research and facilitate transition from lab to real-world buildings.

Abstract

Commercial buildings account for 17% of U.S. carbon emissions, with roughly half of that from Heating, Ventilation, and Air Conditioning (HVAC). HVAC devices form a complex thermodynamic system, and while Model Predictive Control and Reinforcement Learning have been used to optimize control policies, scaling to thousands of buildings remains a significant unsolved challenge. Most current algorithms are over-optimized for specific buildings and rely on proprietary data or hard-to-configure simulations. We present the Smart Buildings Control Suite, the first open source interactive HVAC control benchmark with a focus on solutions that scale. It consists of 3 components: real-world telemetric data extracted from 11 buildings over 6 years, a lightweight data-driven simulator for each building, and a modular Physically Informed Neural Network (PINN) building model as a simulator alternative. The buildings span a variety of climates, management systems, and sizes, and both the simulator and PINN easily scale to new buildings, ensuring solutions using this benchmark are robust to these factors and only reliant on fully scalable building models. This represents a major step towards scaling HVAC optimization from the lab to buildings everywhere. To facilitate use, our benchmark is compatible with the Gym standard, and our data is part of TensorFlow Datasets.

Figures (32)

• Figure 1: Visualization of an Environment. Colder temperatures are blue; warmer ones are red. Blue and red dots inside the building indicate diffusers dispensing cold and warm air respectively.
• Figure 2: Thermal model for simulation. A building consists of conditioned zones, where the mean temperature of the zone $T_z$ should be within upper and lower setpoints, $\hat{T}_{z, max}$ and $\hat{T}_{z,min}$. Thermal power for heating or cooling the room is supplied to each zone, $\dot{Q}_s$, and recirculated from the zone, $\dot{Q}_r$ from the HVAC system, with additional thermal exchange $\dot{Q}_z$ from walls, doors, etc. The AHU supplies the building with air at supply air temperature setpoint $\hat{T}_s$ drawing fresh outside air, $\dot{m}_{OA}$, at temperatures, $T_{OA}$, and returning exhaust air $\dot{m}_{exhaust}$ at temperature $T_{exhaust}$ to the outside using intake and exhaust fans, $\dot{W}_{a,in}$ and $\dot{W}_{a,out}$. A fraction of the return air can be recirculated, $\dot{m}_{recirc}$. Central air conditioning is achieved with a chiller and pump that join a refrigeration cycle to the supply air, consuming electrical energy for the AC compressor $\dot{W}_{c}$ and coolant circulation, $\dot{W}_{c,p}$. The hot water cycle consists of a boiler that maintains the supply water temperature at $T_b$ heated by natural gas power $\dot{Q}_{b}$, and a pump that circulates hot water through the building, with electrical power $\dot{W}_{b,p}$. Supply air is delivered to zones through VAVs.
• Figure 3: Drift Over 48 hrs on Train Set
• Figure 4: Drift Over 24 hrs on Validation Set
• Figure 5: Visualization of simulator drift after 24 hours on validation data. A heat map represents the temperature difference between the simulator and the real world, with red indicating the simulator is hotter, blue indicating it is colder, and white indicating no difference. The zones with the max and min differences are indicated by displaying the difference above them.