Presentation 2015-01-15
Operating state estimation of electric appliances based on power-time-series at a distribution board
Hiroshi INOUE, Fumihiko ISHIYAMA, Toshio WATANABE, Takashi OHYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We study a method based on the naive Bayes classifier for estimating an On/Off state of air-conditioners by using statistical features extracted from time series of aggregated power consumption of a household. A method utilizing duration of the high power state is proposed. The estimation accuracy is evaluated using a probabilistic classifier as estimation model AODE (Averaged One-Dependence Estimators), and the effectiveness of the proposed method is confirmed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Electric Power / State Estimation / Feature Value / AODE
Paper # ICM2014-35,LOIS2014-42
Date of Issue

Conference Information
Committee LOIS
Conference Date 2015/1/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Life Intelligence and Office Information Systems (LOIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Operating state estimation of electric appliances based on power-time-series at a distribution board
Sub Title (in English)
Keyword(1) Electric Power
Keyword(2) State Estimation
Keyword(3) Feature Value
Keyword(4) AODE
1st Author's Name Hiroshi INOUE
1st Author's Affiliation NTT Energy and Environment Systems Laboratories()
2nd Author's Name Fumihiko ISHIYAMA
2nd Author's Affiliation NTT Energy and Environment Systems Laboratories
3rd Author's Name Toshio WATANABE
3rd Author's Affiliation NTT Energy and Environment Systems Laboratories
4th Author's Name Takashi OHYAMA
4th Author's Affiliation NTT Energy and Environment Systems Laboratories
Date 2015-01-15
Paper # ICM2014-35,LOIS2014-42
Volume (vol) vol.114
Number (no) 390
Page pp.pp.-
#Pages 4
Date of Issue