Cross-domain feature selection and coding for household energy behavior

Xing Tong, Ran Li, Furong Li, Chongqing Kang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Household energy behavior is a key factor that dictates energy consumption, efficiency and conservation. In the past, household energy behavior was typically unknown because conventional meters only recorded the total amount of energy consumed for a household over a significant period of time. The rollout of smart meters enabled real-time household energy consumption to be recorded and analyzed. This paper uses smart meter readings from more than 5000 Irish households to identify energy behavior indicators through a cross-domain feature selection and coding approach. The idea is to extract and connect customers' features from energy domain and demography domain, i.e., smart metering data and household information. Smart metering data are characterized by typical energy spectral patterns, whereas household information is encoded as the energy behavior indicator. The results show that employment status and internet usage are highly correlated with household energy behavior in Ireland because employment status and internet usage have an important effect on lifestyle, including when to work, play, and rest, and hence yield a difference in electricity use style. The proposed approach offers a simple, transparent and effective alternative to a challenging cross-domain matching problem with massive smart metering data and energy behavior indicators.

Original languageEnglish
Pages (from-to)9-16
Number of pages8
JournalEnergy
Volume107
DOIs
Publication statusPublished - 15 Jul 2016

Fingerprint

Smart meters
Feature extraction
Energy utilization
Internet
Conservation
Electricity

Keywords

  • Customer classification
  • Demographic factors
  • Feature selection and coding
  • Household energy behavior

Cite this

Cross-domain feature selection and coding for household energy behavior. / Tong, Xing; Li, Ran; Li, Furong; Kang, Chongqing.

In: Energy, Vol. 107, 15.07.2016, p. 9-16.

Research output: Contribution to journalArticle

@article{3742918d5546488da5507a7f0f186ade,
title = "Cross-domain feature selection and coding for household energy behavior",
abstract = "Household energy behavior is a key factor that dictates energy consumption, efficiency and conservation. In the past, household energy behavior was typically unknown because conventional meters only recorded the total amount of energy consumed for a household over a significant period of time. The rollout of smart meters enabled real-time household energy consumption to be recorded and analyzed. This paper uses smart meter readings from more than 5000 Irish households to identify energy behavior indicators through a cross-domain feature selection and coding approach. The idea is to extract and connect customers' features from energy domain and demography domain, i.e., smart metering data and household information. Smart metering data are characterized by typical energy spectral patterns, whereas household information is encoded as the energy behavior indicator. The results show that employment status and internet usage are highly correlated with household energy behavior in Ireland because employment status and internet usage have an important effect on lifestyle, including when to work, play, and rest, and hence yield a difference in electricity use style. The proposed approach offers a simple, transparent and effective alternative to a challenging cross-domain matching problem with massive smart metering data and energy behavior indicators.",
keywords = "Customer classification, Demographic factors, Feature selection and coding, Household energy behavior",
author = "Xing Tong and Ran Li and Furong Li and Chongqing Kang",
year = "2016",
month = "7",
day = "15",
doi = "10.1016/j.energy.2016.03.135",
language = "English",
volume = "107",
pages = "9--16",
journal = "Energy",
issn = "0360-5442",
publisher = "Elsevier",

}

TY - JOUR

T1 - Cross-domain feature selection and coding for household energy behavior

AU - Tong, Xing

AU - Li, Ran

AU - Li, Furong

AU - Kang, Chongqing

PY - 2016/7/15

Y1 - 2016/7/15

N2 - Household energy behavior is a key factor that dictates energy consumption, efficiency and conservation. In the past, household energy behavior was typically unknown because conventional meters only recorded the total amount of energy consumed for a household over a significant period of time. The rollout of smart meters enabled real-time household energy consumption to be recorded and analyzed. This paper uses smart meter readings from more than 5000 Irish households to identify energy behavior indicators through a cross-domain feature selection and coding approach. The idea is to extract and connect customers' features from energy domain and demography domain, i.e., smart metering data and household information. Smart metering data are characterized by typical energy spectral patterns, whereas household information is encoded as the energy behavior indicator. The results show that employment status and internet usage are highly correlated with household energy behavior in Ireland because employment status and internet usage have an important effect on lifestyle, including when to work, play, and rest, and hence yield a difference in electricity use style. The proposed approach offers a simple, transparent and effective alternative to a challenging cross-domain matching problem with massive smart metering data and energy behavior indicators.

AB - Household energy behavior is a key factor that dictates energy consumption, efficiency and conservation. In the past, household energy behavior was typically unknown because conventional meters only recorded the total amount of energy consumed for a household over a significant period of time. The rollout of smart meters enabled real-time household energy consumption to be recorded and analyzed. This paper uses smart meter readings from more than 5000 Irish households to identify energy behavior indicators through a cross-domain feature selection and coding approach. The idea is to extract and connect customers' features from energy domain and demography domain, i.e., smart metering data and household information. Smart metering data are characterized by typical energy spectral patterns, whereas household information is encoded as the energy behavior indicator. The results show that employment status and internet usage are highly correlated with household energy behavior in Ireland because employment status and internet usage have an important effect on lifestyle, including when to work, play, and rest, and hence yield a difference in electricity use style. The proposed approach offers a simple, transparent and effective alternative to a challenging cross-domain matching problem with massive smart metering data and energy behavior indicators.

KW - Customer classification

KW - Demographic factors

KW - Feature selection and coding

KW - Household energy behavior

UR - http://www.scopus.com/inward/record.url?scp=84963854300&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1016/j.energy.2016.03.135

U2 - 10.1016/j.energy.2016.03.135

DO - 10.1016/j.energy.2016.03.135

M3 - Article

AN - SCOPUS:84963854300

VL - 107

SP - 9

EP - 16

JO - Energy

JF - Energy

SN - 0360-5442

ER -