Loading...
A novel deep learning framework with a COVID-19 adjustment for electricity demand forecasting
Cui, Zhesen Wu, Jinran Lian, Wei Wang, You-Gan
Cui, Zhesen
Wu, Jinran
Lian, Wei
Wang, You-Gan
Abstract
Electricity demand forecasting is crucial for practical power system management. However, during the COVID-19 pandemic, the electricity demand system deviated from normal system, which has detrimental bias effect in future forecasts. To overcome this problem, we propose a deep learning framework with a COVID-19 adjustment for electricity demand forecasting. More specifically, we first designed COVID-19 related variables and applied a multiple linear regression model. After eliminating the impact of COVID-19, we employed an efficient deep learning algorithm, long short-term memory multiseasonal net deseasonalized approach, to model residuals from the linear model aforementioned. Finally, we demonstrated the merits of the proposed framework using the electricity demand in Taixing, Jiangsu, China, from May 13, 2018 to August 2, 2021.
Keywords
time series modeling, pandemic, deep learning, load forecasting
Date
2023
Type
Journal article
Journal
Book
Volume
9
Issue
Page Range
1887-1895
Article Number
ACU Department
Institute for Positive Psychology and Education
Faculty of Education and Arts
Institute for Learning Sciences and Teacher Education (ILSTE)
Faculty of Education and Arts
Institute for Learning Sciences and Teacher Education (ILSTE)
Relation URI
Source URL
Event URL
Open Access Status
Published as ‘gold’ (paid) open access
License
CC BY 4.0
File Access
Open