Electricity usage type selection and model validation based on electricity usage measurements

Teemu Mutanen; Tomi Sorasalmi; Robert Weiss

Electricity usage type selection and model validation based on electricity usage measurements

Teemu Mutanen, Tomi Sorasalmi, Robert Weiss

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

In a smart gird environment, the hourly electricity consumption measurements are used for detection of user segments and of a possible underlying distribution. Electricity usages are segmented according to the daily behaviour. The resulted segments indicate that electricity consumption is distributed differently in different segments. The results show that the electricity consumption is distributed based on a log-normal distribution in some segments and in some subsamples inside the segment. The information can be used as the basis when training other models

Original language	English
Title of host publication	Advances in Data Mining, Poster and Industry Proceedings 2012
Publisher	IbaI Publishing
Pages	52-60
ISBN (Print)	978-3-942952-17-0
Publication status	Published - 2012
MoE publication type	A4 Article in a conference publication
Event	12th Industrial Conference on Advances in Data Mining, ICDM 2012 - Berlin, Germany Duration: 13 Jul 2012 → 20 Jul 2012

Conference

Conference	12th Industrial Conference on Advances in Data Mining, ICDM 2012
Abbreviated title	ICDM 2012
Country/Territory	Germany
City	Berlin
Period	13/07/12 → 20/07/12

Keywords

high frequency data
electricity measurements
classication
log-normal distribution
model validation

UN SDGs

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

Cite this

@inproceedings{016c738dd5a34a23a5d139fca698eebf,

title = "Electricity usage type selection and model validation based on electricity usage measurements",

abstract = "In a smart gird environment, the hourly electricity consumption measurements are used for detection of user segments and of a possible underlying distribution. Electricity usages are segmented according to the daily behaviour. The resulted segments indicate that electricity consumption is distributed differently in different segments. The results show that the electricity consumption is distributed based on a log-normal distribution in some segments and in some subsamples inside the segment. The information can be used as the basis when training other models",

keywords = "high frequency data, electricity measurements, classication, log-normal distribution, model validation",

author = "Teemu Mutanen and Tomi Sorasalmi and Robert Weiss",

note = "Project code: 78244; 12th Industrial Conference on Advances in Data Mining, ICDM 2012, ICDM 2012 ; Conference date: 13-07-2012 Through 20-07-2012",

year = "2012",

language = "English",

isbn = "978-3-942952-17-0",

pages = "52--60",

booktitle = "Advances in Data Mining, Poster and Industry Proceedings 2012",

publisher = "IbaI Publishing",

address = "Germany",

}

Electricity usage type selection and model validation based on electricity usage measurements. / Mutanen, Teemu; Sorasalmi, Tomi; Weiss, Robert.
Advances in Data Mining, Poster and Industry Proceedings 2012. IbaI Publishing, 2012. p. 52-60.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Electricity usage type selection and model validation based on electricity usage measurements

AU - Mutanen, Teemu

AU - Sorasalmi, Tomi

AU - Weiss, Robert

N1 - Project code: 78244

PY - 2012

Y1 - 2012

N2 - In a smart gird environment, the hourly electricity consumption measurements are used for detection of user segments and of a possible underlying distribution. Electricity usages are segmented according to the daily behaviour. The resulted segments indicate that electricity consumption is distributed differently in different segments. The results show that the electricity consumption is distributed based on a log-normal distribution in some segments and in some subsamples inside the segment. The information can be used as the basis when training other models

AB - In a smart gird environment, the hourly electricity consumption measurements are used for detection of user segments and of a possible underlying distribution. Electricity usages are segmented according to the daily behaviour. The resulted segments indicate that electricity consumption is distributed differently in different segments. The results show that the electricity consumption is distributed based on a log-normal distribution in some segments and in some subsamples inside the segment. The information can be used as the basis when training other models

KW - high frequency data

KW - electricity measurements

KW - classication

KW - log-normal distribution

KW - model validation

UR - http://ibai-publishing.org/html/proceeding2012.php

M3 - Conference article in proceedings

SN - 978-3-942952-17-0

SP - 52

EP - 60

BT - Advances in Data Mining, Poster and Industry Proceedings 2012

PB - IbaI Publishing

T2 - 12th Industrial Conference on Advances in Data Mining, ICDM 2012

Y2 - 13 July 2012 through 20 July 2012

ER -

Electricity usage type selection and model validation based on electricity usage measurements

Abstract

Conference

Keywords

UN SDGs

Other files and links

Fingerprint

Cite this