Presentation 2016-01-29
Analysis of Family Electricity Data Obtained by Smart Meters
Kazuki Omomo, Yuta Kobiyama, Qiangfu Zhao,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, by using electricity data obtained by smart meters located in residential houses, we try to predict future amount of electricity. If we can predict it correctly for all families, we promise to improve the accuracy of the prediction for all over the region and to reduce the cost of electricity generation for electricity companies. As prediction methods, we investigate a method using Support Vector Regressions (SVRs) and a method using Autoregressive Integrated Moving Average (ARIMA) models. Then we compare these methods. Experimental results show that for single-person families, it is almost impossible to predict the electricity, even if we use non-linear models like SVR. For multi-person families, on the other hands, we can predict the electricity relatively welleven if we use linear model like ARIMA.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Smart meter / Electricity consumption / Support vector regression / ARIMA model
Paper # ASN2015-90
Date of Issue 2016-01-21 (ASN)

Conference Information
Committee MICT / ASN / MoNA
Conference Date 2016/1/28(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Hotel Okada
Topics (in Japanese) (See Japanese page)
Topics (in English) Ambient intelligence, ICT for Medical, Healthcare and Sports, etc
Chair Ryuji Kohno(Yokohama National Univ.) / Hiroshi Tohjo(NTT) / Hiroaki Morino(Shibaura Inst. of Tech.)
Vice Chair Masaru Sugimachi(National Cerebral and Cardiovascular Center) / Takahiro Aoyagi(Tokyo Inst. of Tech.) / Hiroo Sekiya(Chiba Univ.) / Hiraku Okada(Nagoya Univ.) / Kiyohito Yoshihara(KDDI R&D Labs.) / Ryoichi Shinkuma(Kyoto Univ.)
Secretary Masaru Sugimachi(NICT) / Takahiro Aoyagi(Nagoya Inst. of Tech.) / Hiroo Sekiya(Kanagawa Inst. of Tech.) / Hiraku Okada(NTT) / Kiyohito Yoshihara(KDDI R&D Labs.) / Ryoichi Shinkuma(Kumamoto Univ.)
Assistant Kohei Ohno(Meiji Univ.) / Keisuke Shima(Yokohama National Univ.) / Tomoko Tateyama(Ritsumeikan Univ.) / Yuichi Igarashi(Hitachi) / Katsuhiro Naito(Aichi Inst. of Tech.) / Kiyohiko Hattori(NICT) / Hiroshi Fujita(Fujitsu Labs.) / Takuro Yonezawa(Keio Univ.) / Yoshifumi Morihiro(NTT DoCoMo) / Hisashi Kurasawa(NTT) / Makoto Suzuki(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Healthcare and Medical Information Communication Technology / Technical Committee on Ambient intelligence and Sensor Networks / Technical Committee on Mobile Network and Applications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analysis of Family Electricity Data Obtained by Smart Meters
Sub Title (in English)
Keyword(1) Smart meter
Keyword(2) Electricity consumption
Keyword(3) Support vector regression
Keyword(4) ARIMA model
1st Author's Name Kazuki Omomo
1st Author's Affiliation University of Aizu(Univ. Aizu)
2nd Author's Name Yuta Kobiyama
2nd Author's Affiliation University of Aizu(Univ. Aizu)
3rd Author's Name Qiangfu Zhao
3rd Author's Affiliation University of Aizu(Univ. Aizu)
Date 2016-01-29
Paper # ASN2015-90
Volume (vol) vol.115
Number (no) ASN-437
Page pp.pp.63-68(ASN),
#Pages 6
Date of Issue 2016-01-21 (ASN)