Abstract
Heating, ventilation, and air-conditioning (HVAC) and electric water heating (EWH) represent residential loads. Simulating these appliances for electric load forecasting, demand response (DR) studies, and human behavior analysis using physics-based models and artificial intelligence (AI) can further advance smart home technology. This paper explains the background of residential load modeling, starting with the concept of digital twin (DT) as well as the different types of methods. Two major types of appliance load monitoring (ALM) and their advantages/disadvantages are then discussed. This is followed by a review of multiple studies on residential load modeling, particularly for HVAC, EWH, and human behavior. Further examples of electric load forecasts and DR case studies using experimental smart homes are provided. The results and impact of these studies are discussed, as well as their contribution to the advancement of smart home technology and large-scale application.
Document Type
Conference Proceeding
Publication Date
2022
Digital Object Identifier (DOI)
https://doi.org/10.1109/ICRERA55966.2022.9922831
Repository Citation
Poore, Steven; Alden, Rosemary E.; Gong, Huangjie; and Ionel, Dan M., "Multi-Physics and Artificial Intelligence Models for Digital Twin Implementations of Residential Electric Loads" (2022). Power and Energy Institute of Kentucky Faculty Publications. 81.
https://uknowledge.uky.edu/peik_facpub/81
Notes/Citation Information
Poore, S. B., Alden, R. E., Gong, H., and Ionel, D. M., “Multi-Physics and Artificial Intelligence Models for Digital Twin Implementations of Residential Electric Loads”, Proceedings, IEEE ICRERA, Istanbul, TR, doi: 10.1109/ICRERA55966.2022.9922831, pp. 576-581 (Sep 2022)