Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Learning-based framework for sensor fault-tolerant building HVAC control with model-assisted learning

Conference · · Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

As people spend up to 87% of their time indoors, intelligent Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings are essential for maintaining occupant comfort and reducing energy consumption. These HVAC systems in smart buildings rely 'on real-time sensor readings, which in practice often suffer from various faults and could also be vulnerable to malicious attacks. Such faulty sensor inputs may lead to the violation of indoor environment requirements (e.g., temperature, humidity, etc.) and the increase of energy consumption. While many model-based approaches have been proposed in the literature for building HVAC control, it is costly to develop accurate physical models for ensuring their performance and even more challenging to address the impact of sensor faults. In this work, we present a novel learning-based framework for sensor fault-tolerant HVAC control, which includes three deep learning based components for 1) generating temperature proposals with the consideration of possible sensor faults, 2) selecting one of the proposals based on the assessment of their accuracy, and 3) applying reinforcement learning with the selected temperature proposal. Moreover, to address the challenge of training data insufficiency in building-related tasks, we propose a model-assisted learning method leveraging an abstract model of building physical dynamics. Through extensive experiments, we demonstrate that the proposed fault-tolerant HVAC control framework can significantly reduce building temperature violations under a variety of sensor fault patterns while maintaining energy efficiency.

Research Organization:
Texas A & M Univ., College Station, TX (United States). Texas A & M Engineering Experiment Station
Sponsoring Organization:
USDOE
DOE Contract Number:
EE0009150
OSTI ID:
2331287
Journal Information:
Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, Conference: The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys ’21), November 17–18, 2021, Coimbra, Portugal.
Country of Publication:
United States
Language:
English

References (15)

Transfer learning with deep neural networks for model predictive control of HVAC and natural ventilation in smart buildings May 2020
Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks April 2014
Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis March 2014
DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings Via Reinforcement Learning September 2020
The National Human Activity Pattern Survey (NHAPS): a resource for assessing exposure to environmental pollutants July 2001
Model-Based Hierarchical Optimal Control Design for HVAC Systems May 2012
Fault detection and diagnosis of large-scale HVAC systems in buildings using data-driven methods: A comprehensive review December 2020
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation December 2015
Model-Based Predictive Control for building energy management. I: Energy modeling and optimal control December 2016
Fault-tolerant control for outdoor ventilation air flow rate in buildings based on neural network July 2002
Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method November 2005
Deep Reinforcement Learning for Building HVAC Control June 2017
Co-simulation of building energy and control systems with the Building Controls Virtual Test Bed September 2011
Users Manual for TMY3 Data Sets (Revised) May 2008
One for Many November 2020