An official website of the United States government
Good indoor air quality in office environments is essential for occupant health and productivity. In open-plan offices, displacement ventilation has been recognized for its higher efficiency compared to mixing ventilation. This study evaluates the performance of displacement ventilation in an open-plan office under cooling and heating conditions, considering various supply ventilation rates, supply air temperatures, and occupancy levels. Field measurements were conducted over three months in a living laboratory office in a high-performance building. The indoor environment was controlled by an independent variable air volume (VAV) air conditioning system. The supply ventilation rate ranged from 6 to 12 h^−1. Real-time measurements of carbon dioxide (CO2) concentrations in the supply air, return air, and breathing zone of the office were conducted to assess occupants’ exposure to CO2 and ventilation efficiency. The results show that the supply ventilation rate plays an important role in shaping the air distribution and overall effectiveness of the mechanical ventilation system. Higher supply ventilation rates can enhance air distribution robustness, improving ventilation efficiency and reducing CO2 exposure under both cooling and heating conditions. These findings also suggest the need for an optimized control logic that differs from the conventional control logic used in VAV systems. Specifically, during the heating condition of displacement ventilation, it is recommended to maintain the supply ventilation rate at a higher level to effectively mitigate the impact of occupant behavior on air quality, minimize CO2 exposure risks, and ensure a more robust and reliable indoor air distribution.
more »
« less
This content will become publicly available on February 1, 2027
Operator learning for energy-efficient building ventilation control with computational fluid dynamics simulation of a real-world classroom
Energy-efficient ventilation control plays a vital role in reducing building energy consumption while ensuring occupant health and comfort. While Computational Fluid Dynamics (CFD) simulations provide detailed and physically accurate representations of indoor airflow, their high computational cost limits their use in real-time building control. In this work, we present a neural operator learning framework that combines the physical accuracy of CFD with the computational efficiency of machine learning to enable building ventilation control with the high-fidelity fluid dynamics models. Our method jointly optimizes the airflow supply rates and vent angles to reduce energy use and adhere to air quality constraints. We train an ensemble of neural operator transformer models to learn the mapping from building control actions to airflow fields using high-resolution CFD data. This learned neural operator is then embedded in an optimization-based control framework for building ventilation control. Experimental results show that our approach achieves significant energy savings compared to maximum airflow rate control, rule-based control, as well as data-driven control methods using spatially averaged CO2 prediction and deep learning–based reduced-order models, while consistently maintaining safe indoor air quality. These results highlight the practicality and scalability of our method in maintaining energy efficiency and indoor air quality in real-world buildings.
more »
« less
- Award ID(s):
- 2442689
- PAR ID:
- 10698204
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Applied Energy
- Volume:
- 404
- Issue:
- C
- ISSN:
- 0306-2619
- Page Range / eLocation ID:
- 127035
- Subject(s) / Keyword(s):
- Building energy systems, Ventilation control, Energy efficiency, Indoor air quality, Neural operator learning
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Cost-effective sensors are capable of real-time capturing a variety of air quality-related modalities from different pollutant concentrations to indoor/outdoor humidity and temperature. Machine learning (ML) models are capable of performing air-quality "ahead-of-time" approximations. Undoubtedly, accurate indoor air quality approximation significantly helps provide a healthy indoor environment, optimize associated energy consumption, and offer human comfort. However, it is crucial to design an ML architecture to capture the domain knowledge, so-called problem physics. In this study, we propose six novel physics-based ML models for accurate indoor pollutant concentration approximations. The proposed models include an adroit combination of state-space concepts in physics, Gated Recurrent Units, and Decomposition techniques. The proposed models were illustrated using data collected from five offices in a commercial building in California. The proposed models are shown to be less complex, computationally more efficient, and more accurate than similar state-of-the-art transformer-based models. The superiority of the proposed models is due to their relatively light architecture (computational efficiency) and, more importantly, their ability to capture the underlying highly nonlinear patterns embedded in the often contaminated sensor-collected indoor air quality temporal data.more » « less
-
Commercial HVAC systems intended to mitigate indoor air pollution are operated based on standards that exclude aerosols with smaller diameters, such as ultrafine particles (UFPs, Dp ≤ 100 nm), which dominate a large proportion of indoor and outdoor number-based particle size distributions. UFPs generated from occupant activities or infiltrating from the outdoors can be recirculated and accumulate indoors when they are not successfully filtered by an air handling unit. Monitoring UFPs in real occupied environments is vital to understanding these source and mitigation dynamics, but capturing their rapid transience across multiple locations can be challenging due to high-cost instrumentation. This 9-month field measurement campaign pairs four medium-cost diffusion charger sensors with volumetric airflow rates modulated and monitored in a cloud-based building automation system of an open-plan living laboratory office and dedicated air handling unit to evaluate spatiotemporal particle number and surface area concentrations and migration trends. Particle number flux rates reveal that an estimated daily median of 8 × 10^13 UFPs enter the air handling unit from the outdoors. Switching from a MERV14 to a HEPA filter reduces the number of UFPs supplied to the room by tens of trillions of UFPs daily, increasing the median filtration efficiency from 40% to 96%. These results demonstrate the efficacy of an optimal air handling unit’s performance to improve indoor air quality, while highlighting UFP dynamics that are not accounted for in current filtration standards nor in occupant-centered HVAC control. Scalable sensor development can popularize UFP monitoring and allow for future UFP integration within building control and automation platforms. The framework established for this campaign can be used to evaluate particle fluxes considering different analytes.more » « less
-
Natural ventilation is used to cool buildings and cut energy costs by inducing airflow through building openings without the use of mechanical ventilation and cooling systems. However, prior research has documented increased introduction of particles into indoor environments that are naturally ventilated, with associated health consequences. The recently updated ASHRAE Standard 62.1–2019: Ventilation for Acceptable Indoor Air Quality Natural Ventilation Procedure (NVP) prescribes opening sizes as a function of occupant density and geometry for use as a ventilation strategy, a change from the previous standard. The current work quantifies the indoor air quality impacts of implementing the Standard 62.1–2019 Natural Ventilation Procedure in the United States and compares it to the 62.1-specified ventilation rate procedure. This is done via coupled transient simulation of CONTAM 3.4 and EnergyPlus 9.1. Three pollutant classes were identified to represent a broad range of contaminants: outdoor-generated pollutants, pollutants generated indoors by humans, and pollutants generated indoors by the building itself. With boundary conditions from measured weather and outdoor pollutant data for 13 representative locations throughout the U.S., our modeling first found 41%–185% annual average increase in ventilation rates over its mechanical counterpart if the NVP is used across the geometries and occupant densities in the Standard. Due to elevated ventilation rates, the Natural Ventilation Procedure reduced building-generated and occupant-generated contaminant concentrations during occupied hours by an average of 17%–61% compared to the ventilation rate procedure. Outdoor-generated fine particles averaged 2.1–2.5 times the concentrations indoors when using the NVP as compared to mechanical ventilation with a MERV-8 filter and 7.8–10.4 times the concentration of a mechanical system with a MERV-13 filter. Both ventilation rates and concentrations were substantially climate-specific and somewhat window geometry-specific. We further showed that increased filtration is needed in many cases to keep up with increased effective NVP rates in the 2019 Standard if acceptable levels of indoor particles are to be achieved, and we offer suggestions for improving the Standard.more » « less
-
Continuous provision of quality supply air to data center’s IT pod room is a key parameter in ensuring effective data center operation without any down time. Due to number of possible operating conditions and non-linear relations between operating parameters make the working mechanism of data center difficult to optimize energy use. At present industries are using computational fluid dynamics (CFD) to simulate thermal behaviour for all types of operating conditions. The focus of this study is to predict Supply Air Temperature using Artificial Neural Network (ANN) which can overcome limitations of CFD such as high cost, need of an expertise and large computation time. For developing ANN, input parameters, number of neurons and hidden layers, activation function and the period of training data set were studied. A commercial CFD software package 6sigma room is used to develop a modular data center consisting of an IT pod room and an air-handling unit. CFD analysis is carried out for different outside air conditions. Historical weather data of 1 year was considered as an input for CFD analysis. The ANN model is “trained” using data generated from these CFD results. The predictions of ANN model and the results of CFD analysis for a set of example scenarios were compared to measure the agreement between the two. The results show that the prediction of ANN model is much faster than full computational fluid dynamics simulations with good prediction accuracy. This demonstrates that ANN is an effective way for predicting the performance of an air handling unit.more » « less
