Privacy-preserving data collection for demand response using self-organizing map

Kengo Okada, Kanae Matsui, Jan Haase, Hiroaki Nishi

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

4 Citations (Scopus)

Abstract

Homomorphic encryption for smart grids has been investigated in many studies. It is possible to estimate the total power consumption in an area without knowing the consumption data of individual households. In the case of demand response (DR), it is important to calculate the total electric power consumption in an area because DR reports are published accordingly to reduce peak power consumption when the demand is high. However, the published data may reveal private information about residents, such as the timings of specific activities (leaving from and returning home), and device details. To overcome this problem, we propose a method specialized to enable energy providers to securely share electric power consumption data. The proposed method uses a self-organizing map (SOM), which is an unsupervised learning method. In order to share power consumption data while preserving privacy, the SOM is shared without the raw data. In this framework, a target accuracy of nearly 3% is achieved, while actual data are not published by any company.

Original languageEnglish
Title of host publicationProceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages652-657
Number of pages6
ISBN (Print)9781479966493
DOIs
Publication statusPublished - 2015 Sep 28
Event13th International Conference on Industrial Informatics, INDIN 2015 - Cambridge, United Kingdom
Duration: 2015 Jul 222015 Jul 24

Other

Other13th International Conference on Industrial Informatics, INDIN 2015
CountryUnited Kingdom
CityCambridge
Period15/7/2215/7/24

Fingerprint

privacy
Data privacy
organizing
Self organizing maps
preserving
Electric power utilization
electric power
Unsupervised learning
Cryptography
learning
grids
time measurement
estimates
Industry

Keywords

  • Data collection
  • Demand response
  • Privacy preserving
  • Self-organizing map
  • Smart grid

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Industrial and Manufacturing Engineering
  • Instrumentation
  • Computer Networks and Communications
  • Control and Systems Engineering

Cite this

Okada, K., Matsui, K., Haase, J., & Nishi, H. (2015). Privacy-preserving data collection for demand response using self-organizing map. In Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015 (pp. 652-657). [7281812] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INDIN.2015.7281812

Privacy-preserving data collection for demand response using self-organizing map. / Okada, Kengo; Matsui, Kanae; Haase, Jan; Nishi, Hiroaki.

Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 652-657 7281812.

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

Okada, K, Matsui, K, Haase, J & Nishi, H 2015, Privacy-preserving data collection for demand response using self-organizing map. in Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015., 7281812, Institute of Electrical and Electronics Engineers Inc., pp. 652-657, 13th International Conference on Industrial Informatics, INDIN 2015, Cambridge, United Kingdom, 15/7/22. https://doi.org/10.1109/INDIN.2015.7281812
Okada K, Matsui K, Haase J, Nishi H. Privacy-preserving data collection for demand response using self-organizing map. In Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 652-657. 7281812 https://doi.org/10.1109/INDIN.2015.7281812
Okada, Kengo ; Matsui, Kanae ; Haase, Jan ; Nishi, Hiroaki. / Privacy-preserving data collection for demand response using self-organizing map. Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 652-657
@inproceedings{1e1a9fd0a0074d739421f680ca23d5f0,
title = "Privacy-preserving data collection for demand response using self-organizing map",
abstract = "Homomorphic encryption for smart grids has been investigated in many studies. It is possible to estimate the total power consumption in an area without knowing the consumption data of individual households. In the case of demand response (DR), it is important to calculate the total electric power consumption in an area because DR reports are published accordingly to reduce peak power consumption when the demand is high. However, the published data may reveal private information about residents, such as the timings of specific activities (leaving from and returning home), and device details. To overcome this problem, we propose a method specialized to enable energy providers to securely share electric power consumption data. The proposed method uses a self-organizing map (SOM), which is an unsupervised learning method. In order to share power consumption data while preserving privacy, the SOM is shared without the raw data. In this framework, a target accuracy of nearly 3{\%} is achieved, while actual data are not published by any company.",
keywords = "Data collection, Demand response, Privacy preserving, Self-organizing map, Smart grid",
author = "Kengo Okada and Kanae Matsui and Jan Haase and Hiroaki Nishi",
year = "2015",
month = "9",
day = "28",
doi = "10.1109/INDIN.2015.7281812",
language = "English",
isbn = "9781479966493",
pages = "652--657",
booktitle = "Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Privacy-preserving data collection for demand response using self-organizing map

AU - Okada, Kengo

AU - Matsui, Kanae

AU - Haase, Jan

AU - Nishi, Hiroaki

PY - 2015/9/28

Y1 - 2015/9/28

N2 - Homomorphic encryption for smart grids has been investigated in many studies. It is possible to estimate the total power consumption in an area without knowing the consumption data of individual households. In the case of demand response (DR), it is important to calculate the total electric power consumption in an area because DR reports are published accordingly to reduce peak power consumption when the demand is high. However, the published data may reveal private information about residents, such as the timings of specific activities (leaving from and returning home), and device details. To overcome this problem, we propose a method specialized to enable energy providers to securely share electric power consumption data. The proposed method uses a self-organizing map (SOM), which is an unsupervised learning method. In order to share power consumption data while preserving privacy, the SOM is shared without the raw data. In this framework, a target accuracy of nearly 3% is achieved, while actual data are not published by any company.

AB - Homomorphic encryption for smart grids has been investigated in many studies. It is possible to estimate the total power consumption in an area without knowing the consumption data of individual households. In the case of demand response (DR), it is important to calculate the total electric power consumption in an area because DR reports are published accordingly to reduce peak power consumption when the demand is high. However, the published data may reveal private information about residents, such as the timings of specific activities (leaving from and returning home), and device details. To overcome this problem, we propose a method specialized to enable energy providers to securely share electric power consumption data. The proposed method uses a self-organizing map (SOM), which is an unsupervised learning method. In order to share power consumption data while preserving privacy, the SOM is shared without the raw data. In this framework, a target accuracy of nearly 3% is achieved, while actual data are not published by any company.

KW - Data collection

KW - Demand response

KW - Privacy preserving

KW - Self-organizing map

KW - Smart grid

UR - http://www.scopus.com/inward/record.url?scp=84949512680&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949512680&partnerID=8YFLogxK

U2 - 10.1109/INDIN.2015.7281812

DO - 10.1109/INDIN.2015.7281812

M3 - Conference contribution

AN - SCOPUS:84949512680

SN - 9781479966493

SP - 652

EP - 657

BT - Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -