A study on the practical use of smart meter end-user demand data

Geunyeong Park; Donghwi Jung; Sanghoon Jun

doi:10.3741/JKWRA.2021.54.10.759

A study on the practical use of smart meter end-user demand data

Geunyeong Park
, Donghwi Jung^*
, Sanghoon Jun

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

This work introduces a new approach that classifies individual household water usage by examining the characteristics of smart meter end-user demand data. Here, one of the most well-known unsupervised machine learning, K-means algorithm, is applied to classify water consumptions by each household. The intensity and duration of end-user demands are used as main features to determine the households with similar water consumption pattern. The results showed that 21 households are classified into 13 clusters with each cluster having one, two, three, or five houses. The reasoning why multiple households are classified into the same cluster is described in this paper with respect to the collected data and end-user water consumption behavior.

Original language	English
Pages (from-to)	759-768
Number of pages	10
Journal	Journal of Korea Water Resources Association
Volume	54
Issue number	10
DOIs	https://doi.org/10.3741/JKWRA.2021.54.10.759
Publication status	Published - 2021 Oct

Bibliographical note

Publisher Copyright:
© 2021 Korea Water Resources Association.

Keywords

End-user demand classification
Smart meter
Unsupervised machine learning
Water distribution system

ASJC Scopus subject areas

Civil and Structural Engineering
Environmental Science (miscellaneous)
Ecological Modelling

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3741/JKWRA.2021.54.10.759

Cite this

@article{fd13ba734c4d44c889c4d5415d415ede,

title = "A study on the practical use of smart meter end-user demand data",

abstract = "This work introduces a new approach that classifies individual household water usage by examining the characteristics of smart meter end-user demand data. Here, one of the most well-known unsupervised machine learning, K-means algorithm, is applied to classify water consumptions by each household. The intensity and duration of end-user demands are used as main features to determine the households with similar water consumption pattern. The results showed that 21 households are classified into 13 clusters with each cluster having one, two, three, or five houses. The reasoning why multiple households are classified into the same cluster is described in this paper with respect to the collected data and end-user water consumption behavior.",

keywords = "End-user demand classification, Smart meter, Unsupervised machine learning, Water distribution system",

author = "Geunyeong Park and Donghwi Jung and Sanghoon Jun",

note = "Publisher Copyright: {\textcopyright} 2021 Korea Water Resources Association.",

year = "2021",

month = oct,

doi = "10.3741/JKWRA.2021.54.10.759",

language = "English",

volume = "54",

pages = "759--768",

journal = "Journal of Korea Water Resources Association",

issn = "2799-8746",

publisher = "Korea Water Resources Association",

number = "10",

}

TY - JOUR

T1 - A study on the practical use of smart meter end-user demand data

AU - Park, Geunyeong

AU - Jung, Donghwi

AU - Jun, Sanghoon

PY - 2021/10

Y1 - 2021/10

N2 - This work introduces a new approach that classifies individual household water usage by examining the characteristics of smart meter end-user demand data. Here, one of the most well-known unsupervised machine learning, K-means algorithm, is applied to classify water consumptions by each household. The intensity and duration of end-user demands are used as main features to determine the households with similar water consumption pattern. The results showed that 21 households are classified into 13 clusters with each cluster having one, two, three, or five houses. The reasoning why multiple households are classified into the same cluster is described in this paper with respect to the collected data and end-user water consumption behavior.

AB - This work introduces a new approach that classifies individual household water usage by examining the characteristics of smart meter end-user demand data. Here, one of the most well-known unsupervised machine learning, K-means algorithm, is applied to classify water consumptions by each household. The intensity and duration of end-user demands are used as main features to determine the households with similar water consumption pattern. The results showed that 21 households are classified into 13 clusters with each cluster having one, two, three, or five houses. The reasoning why multiple households are classified into the same cluster is described in this paper with respect to the collected data and end-user water consumption behavior.

KW - End-user demand classification

KW - Smart meter

KW - Unsupervised machine learning

KW - Water distribution system

UR - https://www.scopus.com/pages/publications/85159362434

U2 - 10.3741/JKWRA.2021.54.10.759

DO - 10.3741/JKWRA.2021.54.10.759

M3 - Article

AN - SCOPUS:85159362434

SN - 2799-8746

VL - 54

SP - 759

EP - 768

JO - Journal of Korea Water Resources Association

JF - Journal of Korea Water Resources Association

IS - 10

ER -

A study on the practical use of smart meter end-user demand data

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this