Clustering methodology for smart metering data based on local and global features

Leticia Arco; Gladys Casas; Ann Nowe

doi:10.1145/3109761.3158398

Clustering methodology for smart metering data based on local and global features

Leticia Arco, Gladys Casas, Ann Nowe

Onderzoeksoutput: Conference paper

3 Citaten (Scopus)

Samenvatting

In order to develop real intelligent smart grids, understanding the patterns hidden in the smart grid data is crucial. More precisely, the detection of the preferences, behavior and characteristics of consumers and prosumers is crucial. In this work, we introduce a general methodology that groups energy consumption and production of households, based on global as well as local features, allowing the characterization of load and production profiles for consumers and prosumers. Our methodology is illustrated using a two-level clustering approach. The theoretical
results are applicable in other areas, and have utility in a general business analysis.

Originele taal-2	English
Titel	IML '17 Proceedings of the 1st International Conference on Internet of Things and Machine Learning
Uitgeverij	Association for Computing Machinery (ACM)
Aantal pagina's	13
ISBN van elektronische versie	978-1-4503-5243-7
DOI's	https://doi.org/10.1145/3109761.3158398
Status	Published - 17 okt. 2017
Evenement	1st International Conference on Internet of Things and Machine Learning - Liverpool, United Kingdom Duur: 17 okt. 2017 → 18 okt. 2017

Conference

Conference	1st International Conference on Internet of Things and Machine Learning
Verkorte titel	IML
Land/Regio	United Kingdom
Stad	Liverpool
Periode	17/10/17 → 18/10/17

Toegang tot document

10.1145/3109761.3158398

EU429: SCANERGY: een schaalbaar en modulair systeem voor energietrading tussen prosumenten
Nowe, A.
1/02/13 → 31/01/17
Project: Fundamenteel

Citeer dit

@inproceedings{8615a725640b46949260e6d4aa037f92,

title = "Clustering methodology for smart metering data based on local and global features",

abstract = "In order to develop real intelligent smart grids, understanding the patterns hidden in the smart grid data is crucial. More precisely, the detection of the preferences, behavior and characteristics of consumers and prosumers is crucial. In this work, we introduce a general methodology that groups energy consumption and production of households, based on global as well as local features, allowing the characterization of load and production profiles for consumers and prosumers. Our methodology is illustrated using a two-level clustering approach. The theoreticalresults are applicable in other areas, and have utility in a general business analysis.",

author = "Leticia Arco and Gladys Casas and Ann Nowe",

year = "2017",

month = oct,

day = "17",

doi = "10.1145/3109761.3158398",

language = "English",

booktitle = "IML '17 Proceedings of the 1st International Conference on Internet of Things and Machine Learning",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "1st International Conference on Internet of Things and Machine Learning, IML ; Conference date: 17-10-2017 Through 18-10-2017",

}

Arco, L, Casas, G & Nowe, A 2017, Clustering methodology for smart metering data based on local and global features. in IML '17 Proceedings of the 1st International Conference on Internet of Things and Machine Learning., 65, Association for Computing Machinery (ACM), 1st International Conference on Internet of Things and Machine Learning, Liverpool, United Kingdom, 17/10/17. https://doi.org/10.1145/3109761.3158398

TY - GEN

T1 - Clustering methodology for smart metering data based on local and global features

AU - Arco, Leticia

AU - Casas, Gladys

AU - Nowe, Ann

PY - 2017/10/17

Y1 - 2017/10/17

N2 - In order to develop real intelligent smart grids, understanding the patterns hidden in the smart grid data is crucial. More precisely, the detection of the preferences, behavior and characteristics of consumers and prosumers is crucial. In this work, we introduce a general methodology that groups energy consumption and production of households, based on global as well as local features, allowing the characterization of load and production profiles for consumers and prosumers. Our methodology is illustrated using a two-level clustering approach. The theoreticalresults are applicable in other areas, and have utility in a general business analysis.

AB - In order to develop real intelligent smart grids, understanding the patterns hidden in the smart grid data is crucial. More precisely, the detection of the preferences, behavior and characteristics of consumers and prosumers is crucial. In this work, we introduce a general methodology that groups energy consumption and production of households, based on global as well as local features, allowing the characterization of load and production profiles for consumers and prosumers. Our methodology is illustrated using a two-level clustering approach. The theoreticalresults are applicable in other areas, and have utility in a general business analysis.

U2 - 10.1145/3109761.3158398

DO - 10.1145/3109761.3158398

M3 - Conference paper

BT - IML '17 Proceedings of the 1st International Conference on Internet of Things and Machine Learning

PB - Association for Computing Machinery (ACM)

T2 - 1st International Conference on Internet of Things and Machine Learning

Y2 - 17 October 2017 through 18 October 2017

ER -

Clustering methodology for smart metering data based on local and global features

Samenvatting

Conference

Toegang tot document

Vingerafdruk

Projecten

EU429: SCANERGY: een schaalbaar en modulair systeem voor energietrading tussen prosumenten

Citeer dit