A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, China
The COVID-19 pandemic has impacted electricity consumption patterns and such an impact cannot be analyzed by simple data analytics. In China, specifically, city lock-down policies lasted for only a few weeks and the spread of COVID-19 was quickly under control. This has made it challenging to analyz...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/14/23/8187 |
_version_ | 1797507784169750528 |
---|---|
author | Zhiang Zhang Ali Cheshmehzangi Saeid Pourroostaei Ardakani |
author_facet | Zhiang Zhang Ali Cheshmehzangi Saeid Pourroostaei Ardakani |
author_sort | Zhiang Zhang |
collection | DOAJ |
description | The COVID-19 pandemic has impacted electricity consumption patterns and such an impact cannot be analyzed by simple data analytics. In China, specifically, city lock-down policies lasted for only a few weeks and the spread of COVID-19 was quickly under control. This has made it challenging to analyze the hidden impact of COVID-19 on electricity consumption. This paper targets the electricity consumption of a group of regions in China and proposes a new clustering-based method to quantitatively investigate the impact of COVID-19 on the industrial-driven electricity consumption pattern. This method performs K-means clustering on time-series electricity consumption data of multiple regions and uses quantitative metrics, including clustering evaluation metrics and dynamic time warping, to quantify the impact and pattern changes. The proposed method is applied to the two-year daily electricity consumption data of 87 regions of Zhejiang province, China, and quantitively confirms COVID-19 has changed the electricity consumption pattern of Zhejiang in both the short-term and long-term. The time evolution of the pattern change is also revealed by the method, so the impact start and end time can be inferred. Results also show the short-term impact of COVID-19 is similar across different regions, while the long-term impact is not. In some regions, the pandemic only caused a time-shift in electricity consumption; but in others, the electricity consumption pattern has been permanently changed. The data-driven analysis of this paper can be the first step to fully interpret the COVID-19 impact by considering economic and social parameters in future studies. |
first_indexed | 2024-03-10T04:54:22Z |
format | Article |
id | doaj.art-7d26c0d9199943f194fee17ac62c4ea8 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T04:54:22Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-7d26c0d9199943f194fee17ac62c4ea82023-11-23T02:23:59ZengMDPI AGEnergies1996-10732021-12-011423818710.3390/en14238187A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, ChinaZhiang Zhang0Ali Cheshmehzangi1Saeid Pourroostaei Ardakani2Department of Architecture and Built Environment, University of Nottingham Ningbo China, Ningbo 315100, ChinaDepartment of Architecture and Built Environment, University of Nottingham Ningbo China, Ningbo 315100, ChinaSchool of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, ChinaThe COVID-19 pandemic has impacted electricity consumption patterns and such an impact cannot be analyzed by simple data analytics. In China, specifically, city lock-down policies lasted for only a few weeks and the spread of COVID-19 was quickly under control. This has made it challenging to analyze the hidden impact of COVID-19 on electricity consumption. This paper targets the electricity consumption of a group of regions in China and proposes a new clustering-based method to quantitatively investigate the impact of COVID-19 on the industrial-driven electricity consumption pattern. This method performs K-means clustering on time-series electricity consumption data of multiple regions and uses quantitative metrics, including clustering evaluation metrics and dynamic time warping, to quantify the impact and pattern changes. The proposed method is applied to the two-year daily electricity consumption data of 87 regions of Zhejiang province, China, and quantitively confirms COVID-19 has changed the electricity consumption pattern of Zhejiang in both the short-term and long-term. The time evolution of the pattern change is also revealed by the method, so the impact start and end time can be inferred. Results also show the short-term impact of COVID-19 is similar across different regions, while the long-term impact is not. In some regions, the pandemic only caused a time-shift in electricity consumption; but in others, the electricity consumption pattern has been permanently changed. The data-driven analysis of this paper can be the first step to fully interpret the COVID-19 impact by considering economic and social parameters in future studies.https://www.mdpi.com/1996-1073/14/23/8187COVID-19electricity demand patternclusteringimpact analysis |
spellingShingle | Zhiang Zhang Ali Cheshmehzangi Saeid Pourroostaei Ardakani A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, China Energies COVID-19 electricity demand pattern clustering impact analysis |
title | A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, China |
title_full | A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, China |
title_fullStr | A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, China |
title_full_unstemmed | A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, China |
title_short | A Data-Driven Clustering Analysis for the Impact of COVID-19 on the Electricity Consumption Pattern of Zhejiang Province, China |
title_sort | data driven clustering analysis for the impact of covid 19 on the electricity consumption pattern of zhejiang province china |
topic | COVID-19 electricity demand pattern clustering impact analysis |
url | https://www.mdpi.com/1996-1073/14/23/8187 |
work_keys_str_mv | AT zhiangzhang adatadrivenclusteringanalysisfortheimpactofcovid19ontheelectricityconsumptionpatternofzhejiangprovincechina AT alicheshmehzangi adatadrivenclusteringanalysisfortheimpactofcovid19ontheelectricityconsumptionpatternofzhejiangprovincechina AT saeidpourroostaeiardakani adatadrivenclusteringanalysisfortheimpactofcovid19ontheelectricityconsumptionpatternofzhejiangprovincechina AT zhiangzhang datadrivenclusteringanalysisfortheimpactofcovid19ontheelectricityconsumptionpatternofzhejiangprovincechina AT alicheshmehzangi datadrivenclusteringanalysisfortheimpactofcovid19ontheelectricityconsumptionpatternofzhejiangprovincechina AT saeidpourroostaeiardakani datadrivenclusteringanalysisfortheimpactofcovid19ontheelectricityconsumptionpatternofzhejiangprovincechina |