Learning-based Framework for Sensor Fault-Tolerant Building HVAC Control with Model-assisted Learning

TL;DR

This paper introduces a novel deep learning framework for sensor fault-tolerant HVAC control in buildings, leveraging model-assisted learning to improve occupant comfort and energy efficiency despite sensor faults.

Contribution

It proposes a new learning-based approach with three deep learning components and a model-assisted training method to handle sensor faults in building HVAC systems.

Findings

Reduces indoor temperature violations under sensor faults

Maintains energy efficiency in HVAC control

Demonstrates robustness across various fault patterns

Abstract

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.