Sparse-coding-based household clustering for demand response services

Shintaro Ikeda, Hiroaki Nishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

For the development of a smart grid, smart meter is a key device to measure the electric power usage of network-connected houses. Smart meters are currently being installed into households, and play the important role for providing a demand response service. A demand response is a necessary service in order to adjust supply-demand balancing because the balance is kept by the cost in the electricity market. Therefore, the customers of the electricity supply companies are expected to be optimally assigned as a group. In this paper, we separate a set of households into clusters as optimally assigned customers. When conducting the clustering, the utilization of unsupervised learning using data from a smart meter is required. In this study, we propose a method of household clustering for a demand response event by sparse coding, which is a type of neural network. The proposed method generates a power consumption model of each household, finds simple relationship distances between households, and conducts hierarchical clustering based on these distances. In addition, to extract the characteristics of fluctuating load usage, we conduct data normalization that cuts off at a fixed load usage of each household. To confirm the effect of the proposed clustering method, the usage tendency of household air conditioning (A/C) units was evaluated.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages744-749
Number of pages6
Volume2016-November
ISBN (Electronic)9781509008735
DOIs
Publication statusPublished - 2016 Nov 15
Event25th IEEE International Symposium on Industrial Electronics, ISIE 2016 - Santa Clara, United States
Duration: 2016 Jun 82016 Jun 10

Other

Other25th IEEE International Symposium on Industrial Electronics, ISIE 2016
CountryUnited States
CitySanta Clara
Period16/6/816/6/10

Fingerprint

Smart meters
Unsupervised learning
Air conditioning
Electric power utilization
Electricity
Neural networks
Costs
Industry

Keywords

  • Demand response
  • Household clustering
  • Smart meter
  • Sparse coding

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

Ikeda, S., & Nishi, H. (2016). Sparse-coding-based household clustering for demand response services. In Proceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016 (Vol. 2016-November, pp. 744-749). [7744982] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIE.2016.7744982

Sparse-coding-based household clustering for demand response services. / Ikeda, Shintaro; Nishi, Hiroaki.

Proceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016. Vol. 2016-November Institute of Electrical and Electronics Engineers Inc., 2016. p. 744-749 7744982.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ikeda, S & Nishi, H 2016, Sparse-coding-based household clustering for demand response services. in Proceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016. vol. 2016-November, 7744982, Institute of Electrical and Electronics Engineers Inc., pp. 744-749, 25th IEEE International Symposium on Industrial Electronics, ISIE 2016, Santa Clara, United States, 16/6/8. https://doi.org/10.1109/ISIE.2016.7744982
Ikeda S, Nishi H. Sparse-coding-based household clustering for demand response services. In Proceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016. Vol. 2016-November. Institute of Electrical and Electronics Engineers Inc. 2016. p. 744-749. 7744982 https://doi.org/10.1109/ISIE.2016.7744982
Ikeda, Shintaro ; Nishi, Hiroaki. / Sparse-coding-based household clustering for demand response services. Proceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016. Vol. 2016-November Institute of Electrical and Electronics Engineers Inc., 2016. pp. 744-749
@inproceedings{a28fcede71034d86a70fc058f41612b1,
title = "Sparse-coding-based household clustering for demand response services",
abstract = "For the development of a smart grid, smart meter is a key device to measure the electric power usage of network-connected houses. Smart meters are currently being installed into households, and play the important role for providing a demand response service. A demand response is a necessary service in order to adjust supply-demand balancing because the balance is kept by the cost in the electricity market. Therefore, the customers of the electricity supply companies are expected to be optimally assigned as a group. In this paper, we separate a set of households into clusters as optimally assigned customers. When conducting the clustering, the utilization of unsupervised learning using data from a smart meter is required. In this study, we propose a method of household clustering for a demand response event by sparse coding, which is a type of neural network. The proposed method generates a power consumption model of each household, finds simple relationship distances between households, and conducts hierarchical clustering based on these distances. In addition, to extract the characteristics of fluctuating load usage, we conduct data normalization that cuts off at a fixed load usage of each household. To confirm the effect of the proposed clustering method, the usage tendency of household air conditioning (A/C) units was evaluated.",
keywords = "Demand response, Household clustering, Smart meter, Sparse coding",
author = "Shintaro Ikeda and Hiroaki Nishi",
year = "2016",
month = "11",
day = "15",
doi = "10.1109/ISIE.2016.7744982",
language = "English",
volume = "2016-November",
pages = "744--749",
booktitle = "Proceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Sparse-coding-based household clustering for demand response services

AU - Ikeda, Shintaro

AU - Nishi, Hiroaki

PY - 2016/11/15

Y1 - 2016/11/15

N2 - For the development of a smart grid, smart meter is a key device to measure the electric power usage of network-connected houses. Smart meters are currently being installed into households, and play the important role for providing a demand response service. A demand response is a necessary service in order to adjust supply-demand balancing because the balance is kept by the cost in the electricity market. Therefore, the customers of the electricity supply companies are expected to be optimally assigned as a group. In this paper, we separate a set of households into clusters as optimally assigned customers. When conducting the clustering, the utilization of unsupervised learning using data from a smart meter is required. In this study, we propose a method of household clustering for a demand response event by sparse coding, which is a type of neural network. The proposed method generates a power consumption model of each household, finds simple relationship distances between households, and conducts hierarchical clustering based on these distances. In addition, to extract the characteristics of fluctuating load usage, we conduct data normalization that cuts off at a fixed load usage of each household. To confirm the effect of the proposed clustering method, the usage tendency of household air conditioning (A/C) units was evaluated.

AB - For the development of a smart grid, smart meter is a key device to measure the electric power usage of network-connected houses. Smart meters are currently being installed into households, and play the important role for providing a demand response service. A demand response is a necessary service in order to adjust supply-demand balancing because the balance is kept by the cost in the electricity market. Therefore, the customers of the electricity supply companies are expected to be optimally assigned as a group. In this paper, we separate a set of households into clusters as optimally assigned customers. When conducting the clustering, the utilization of unsupervised learning using data from a smart meter is required. In this study, we propose a method of household clustering for a demand response event by sparse coding, which is a type of neural network. The proposed method generates a power consumption model of each household, finds simple relationship distances between households, and conducts hierarchical clustering based on these distances. In addition, to extract the characteristics of fluctuating load usage, we conduct data normalization that cuts off at a fixed load usage of each household. To confirm the effect of the proposed clustering method, the usage tendency of household air conditioning (A/C) units was evaluated.

KW - Demand response

KW - Household clustering

KW - Smart meter

KW - Sparse coding

UR - http://www.scopus.com/inward/record.url?scp=85000925746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85000925746&partnerID=8YFLogxK

U2 - 10.1109/ISIE.2016.7744982

DO - 10.1109/ISIE.2016.7744982

M3 - Conference contribution

AN - SCOPUS:85000925746

VL - 2016-November

SP - 744

EP - 749

BT - Proceedings - 2016 IEEE 25th International Symposium on Industrial Electronics, ISIE 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -