Clustering and cluster label prediction for daily electric consumption curves of residential users

Jan Kurzidim; Adam Buruzs; Milos Sipetic; Moritz Wagner

doi:10.57739/978-3-903207-89-9

Clustering and cluster label prediction for daily electric consumption curves of residential users

Jan Kurzidim, Adam Buruzs, Milos Sipetic, Moritz Wagner

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation

Abstract

In this contribution, we used clustering methods to establish daily consumption patterns for residential electrical consumption data. We also implemented classification and regression methods to predict the daily consumption pattern of the next day. We applied three different criteria – clustering-, classifier-/regressor- and domain knowledge-based – to determine the best clustering method and number of clusters, analyzed in depth the properties of that clustering (particularly the daily consumption patterns), and found that regression performs better than classification in the label prediction task. The investigation was designed to yield insights that reduce the complexity of the residential electricity consumer market and that can be applied in demand response actions such as load shifting.

Original language	English
Title of host publication	Intelligente Energie- und Klimastrategien
Subtitle of host publication	Energie – Gebäude – Umwelt
Editors	Hildegard Gremmel-Simon
Place of Publication	Wien
Pages	33-40
Number of pages	8
ISBN (Electronic)	978-3-903207-89-9
DOIs	https://doi.org/10.57739/978-3-903207-89-9
Publication status	Published - Jun 2024
Event	e·nova: Intelligente Energie- und Klimastrategien - FH Burgenland, Pinkafeld, Austria Duration: 12 Jun 2024 → 13 Jun 2024 https://www.fh-burgenland.at/bachelor-energie-und-umweltmanagement/enova/

Conference

Conference	e·nova
Abbreviated title	e-nova 2024
Country/Territory	Austria
City	Pinkafeld
Period	12/06/24 → 13/06/24
Internet address	https://www.fh-burgenland.at/bachelor-energie-und-umweltmanagement/enova/

Research Field

Efficient Buildings and HVAC Technologies

Keywords

Residential
Electric consumption
Patterns
Clustering
Classification
Forecasting
Machine learning

Access to Document

10.57739/978-3-903207-89-9Licence: CC BY

Cite this

@inproceedings{4c488b69703c40a39295c5041f16135b,

title = "Clustering and cluster label prediction for daily electric consumption curves of residential users",

abstract = "In this contribution, we used clustering methods to establish daily consumption patterns for residential electrical consumption data. We also implemented classification and regression methods to predict the daily consumption pattern of the next day. We applied three different criteria – clustering-, classifier-/regressor- and domain knowledge-based – to determine the best clustering method and number of clusters, analyzed in depth the properties of that clustering (particularly the daily consumption patterns), and found that regression performs better than classification in the label prediction task. The investigation was designed to yield insights that reduce the complexity of the residential electricity consumer market and that can be applied in demand response actions such as load shifting.",

keywords = "Residential, Electric consumption, Patterns, Clustering, Classification, Forecasting, Machine learning",

author = "Jan Kurzidim and Adam Buruzs and Milos Sipetic and Moritz Wagner",

year = "2024",

month = jun,

doi = "10.57739/978-3-903207-89-9",

language = "English",

pages = "33--40",

editor = "Hildegard Gremmel-Simon",

booktitle = "Intelligente Energie- und Klimastrategien",

note = "e·nova ; Conference date: 12-06-2024 Through 13-06-2024",

url = "https://www.fh-burgenland.at/bachelor-energie-und-umweltmanagement/enova/",

}

Clustering and cluster label prediction for daily electric consumption curves of residential users. / Kurzidim, Jan; Buruzs, Adam ; Sipetic, Milos et al.
Intelligente Energie- und Klimastrategien: Energie – Gebäude – Umwelt. ed. / Hildegard Gremmel-Simon. Wien, 2024. p. 33-40.

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation

TY - GEN

T1 - Clustering and cluster label prediction for daily electric consumption curves of residential users

AU - Kurzidim, Jan

AU - Buruzs, Adam

AU - Sipetic, Milos

AU - Wagner, Moritz

PY - 2024/6

Y1 - 2024/6

N2 - In this contribution, we used clustering methods to establish daily consumption patterns for residential electrical consumption data. We also implemented classification and regression methods to predict the daily consumption pattern of the next day. We applied three different criteria – clustering-, classifier-/regressor- and domain knowledge-based – to determine the best clustering method and number of clusters, analyzed in depth the properties of that clustering (particularly the daily consumption patterns), and found that regression performs better than classification in the label prediction task. The investigation was designed to yield insights that reduce the complexity of the residential electricity consumer market and that can be applied in demand response actions such as load shifting.

AB - In this contribution, we used clustering methods to establish daily consumption patterns for residential electrical consumption data. We also implemented classification and regression methods to predict the daily consumption pattern of the next day. We applied three different criteria – clustering-, classifier-/regressor- and domain knowledge-based – to determine the best clustering method and number of clusters, analyzed in depth the properties of that clustering (particularly the daily consumption patterns), and found that regression performs better than classification in the label prediction task. The investigation was designed to yield insights that reduce the complexity of the residential electricity consumer market and that can be applied in demand response actions such as load shifting.

KW - Residential

KW - Electric consumption

KW - Patterns

KW - Clustering

KW - Classification

KW - Forecasting

KW - Machine learning

U2 - 10.57739/978-3-903207-89-9

DO - 10.57739/978-3-903207-89-9

M3 - Conference Proceedings with Oral Presentation

SP - 33

EP - 40

BT - Intelligente Energie- und Klimastrategien

A2 - Gremmel-Simon, Hildegard

CY - Wien

T2 - e·nova

Y2 - 12 June 2024 through 13 June 2024

ER -

Clustering and cluster label prediction for daily electric consumption curves of residential users

Abstract

Conference

Research Field

Keywords

Access to Document

Fingerprint

Cite this