IoT-Based Comfort Control and Fault Diagnostics System for Energy-Efficient Homes
Year: 2024
Type: report
Abstract: This project studies an Internet of Things (IoT)-based comfort control and fault diagnostics system (referred as iComfort in this report) for energy-efficient homes. The system delivers an occupant-comfort-oriented thermal environment adaptive to fault scenarios and achieves HVAC energy savings in a cost-effective and straightforward way. This smart iComfort home system consists of the following key features. 1) Cost-effectiveness and scalability of the entire hardware and software system: The system includes low-cost temperature, humidity, and airflow sensors, and a Raspberry Pi-based local hub that interfaces with the cloud and IoT-enabled devices. The cost is low, not only for sensors, but also the costs associated with sensor installation, system setup and commissioning, data communication and storage, and data analytics (e.g., the development of automated fault detection and diagnosis (AFDD), as well as adaptive control strategies that are both computationally efficient and practical to implement). 2) Energy performance and user satisfaction: The system delivers user satisfaction and energy savings. This includes a) ease of use, b) optimal occupant thermal comfort, and c) accurate system feedback (e.g., low false alarm of AFDD strategies). 3) Favorable demonstrated prototype performance: The prototype tested at the Pacific Northwest National Laboratory (PNNL) Lab Homes demonstrates the accuracy of fault detections and diagnoses and shows thermal comfort improvement and energy savings through adaptive and optimal HVAC operations. For the field testing in the PNNL Lab Homes, the sensors were found to work stably and streamed measurements to the cloud every minute. The cloud database had 100% availability and was error-free during the experiment. The project also demonstrated FDD methods for the heat pump system, achieving an accuracy of 90.18% and a detection accuracy of 96.4%, both meeting the required value of 80%. The project also showed that occupancy-based setback strategies and data predictive control can save 14% and 10% of energy, respectively, both demonstrating ≥10% energy savings required. In terms of thermal comfort improvement, unmet hours could be decreased from 2.05℉-hr to 0.22℉-hr, which can improve residents’ thermal comfort under the malfunction of HVAC systems or in the heat wave period.
DOI: 10.2172/2338244
Language: English
Subfield: Building and Construction
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Funder: U.S. Department of Energy
OpenAlex ID: W4395670039