Journal
ENERGY
Volume 231, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.energy.2021.120915
Keywords
COVID-19; Domestic hot water; Artificial neural network
Categories
Funding
- Korea Institute of Energy Research [C12419]
Ask authors/readers for more resources
COVID-19 has changed the daily peak time and amount of domestic hot water usage, with active case number serving as a good indicator for correlating changes. A machine learning model was developed to predict hot water demand based on the severity of COVID-19, showing an increase in demand with higher active cases.
COVID-19 made considerable changes in the lifestyle of people, which have led to a rise in energy use in homes. So, this study investigated the relationship between COVID-19 and domestic hot water demands. For this purpose, a nondimensional and principal component analysis were conducted to find out the influencing factors using demand data before and after COVID-19 from our study site. Analysis showed that the COVID-19 outbreak affected the daily peak time and the amount of domestic hot water usage, the active case number of COVID-19 was a good indicator for correlating the changes in hot water de-mand and patterns. Based on this, a machine learning model with an artificial neural network was developed to predict hot water demand depending on the severity of COVID-19 and the relevant cor-relation was also derived. The model analysis showed that the increase in the number of active cases in the region affected the hot water demand increased at a certain rate and the maximum demand peak in morning during weekdays and weekends decreased. Furthermore, if the number of active cases reached more than 4000, the peak in morning moved to afternoon so that the energy use patterns of weekdays and weekends are assimilated. (c) 2021 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available