A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game

Longfei Wei; Aditya Sundararajan; Arif I. Sarwat; Saroj Biswas; Erfan Ibrahim

doi:10.1109/RWEEK.2017.8088640

A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game

Longfei Wei, Aditya Sundararajan, Arif I. Sarwat, Saroj Biswas, Erfan Ibrahim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

40 Scopus citations

Abstract

Electricity theft is a major contributor of nontechnical losses in the distribution systems of the smart grid. However, owing to the resource-limitations of smart meters and the privacy requirement of electricity usage data, theft detection has become a challenging task for electric utilities. To address this problem, a Distributed Intelligent Framework for Electricity Theft Detection (DIFETD) is proposed and implemented in this paper. It is equipped with Benford's Analysis for initial but powerful diagnostics on smart meter big data. A Stackelberg game-theoretic model is formulated to analyze the strategic interactions between one utility and multiple electricity thieves, which is applied to data flagged suspicious by Benford's Analysis. The Stackelberg equilibrium provides sampling rate and threshold to conduct a Likelihood Ratio Test (LRT) to detect potentially fraudulent meters. The framework is validated on real interval electricity usage data from an electric utility in Florida to filter fraudulent meters in a community.

Original language	English
Title of host publication	Proceedings - 2017 Resilience Week, RWS 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5-11
Number of pages	7
ISBN (Electronic)	9781509060559
DOIs	https://doi.org/10.1109/RWEEK.2017.8088640
State	Published - Oct 27 2017
Externally published	Yes
Event	2017 Resilience Week, RWS 2017 - Wilmington, United States Duration: Sep 18 2017 → Sep 22 2017

Publication series

Name	Proceedings - 2017 Resilience Week, RWS 2017

Conference

Conference	2017 Resilience Week, RWS 2017
Country/Territory	United States
City	Wilmington
Period	09/18/17 → 09/22/17

Funding

This work was supported by the National Science Foundation under Grant CNS-1553494.

Keywords

Benford's Analysis
Likelihood Ratio Test
Stackelberg game
electricity theft
smart meter

Access to Document

10.1109/RWEEK.2017.8088640

Cite this

Wei, L., Sundararajan, A., Sarwat, A. I., Biswas, S., & Ibrahim, E. (2017). A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game. In Proceedings - 2017 Resilience Week, RWS 2017 (pp. 5-11). Article 8088640 (Proceedings - 2017 Resilience Week, RWS 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RWEEK.2017.8088640

@inproceedings{680f47d0208c4d5cab0ede4164ccbf58,

title = "A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game",

abstract = "Electricity theft is a major contributor of nontechnical losses in the distribution systems of the smart grid. However, owing to the resource-limitations of smart meters and the privacy requirement of electricity usage data, theft detection has become a challenging task for electric utilities. To address this problem, a Distributed Intelligent Framework for Electricity Theft Detection (DIFETD) is proposed and implemented in this paper. It is equipped with Benford's Analysis for initial but powerful diagnostics on smart meter big data. A Stackelberg game-theoretic model is formulated to analyze the strategic interactions between one utility and multiple electricity thieves, which is applied to data flagged suspicious by Benford's Analysis. The Stackelberg equilibrium provides sampling rate and threshold to conduct a Likelihood Ratio Test (LRT) to detect potentially fraudulent meters. The framework is validated on real interval electricity usage data from an electric utility in Florida to filter fraudulent meters in a community.",

keywords = "Benford's Analysis, Likelihood Ratio Test, Stackelberg game, electricity theft, smart meter",

author = "Longfei Wei and Aditya Sundararajan and Sarwat, {Arif I.} and Saroj Biswas and Erfan Ibrahim",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 Resilience Week, RWS 2017 ; Conference date: 18-09-2017 Through 22-09-2017",

year = "2017",

month = oct,

day = "27",

doi = "10.1109/RWEEK.2017.8088640",

language = "English",

series = "Proceedings - 2017 Resilience Week, RWS 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5--11",

booktitle = "Proceedings - 2017 Resilience Week, RWS 2017",

}

Wei, L, Sundararajan, A, Sarwat, AI, Biswas, S & Ibrahim, E 2017, A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game. in Proceedings - 2017 Resilience Week, RWS 2017., 8088640, Proceedings - 2017 Resilience Week, RWS 2017, Institute of Electrical and Electronics Engineers Inc., pp. 5-11, 2017 Resilience Week, RWS 2017, Wilmington, United States, 09/18/17. https://doi.org/10.1109/RWEEK.2017.8088640

A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game. / Wei, Longfei; Sundararajan, Aditya; Sarwat, Arif I. et al.
Proceedings - 2017 Resilience Week, RWS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 5-11 8088640 (Proceedings - 2017 Resilience Week, RWS 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game

AU - Wei, Longfei

AU - Sundararajan, Aditya

AU - Sarwat, Arif I.

AU - Biswas, Saroj

AU - Ibrahim, Erfan

PY - 2017/10/27

Y1 - 2017/10/27

N2 - Electricity theft is a major contributor of nontechnical losses in the distribution systems of the smart grid. However, owing to the resource-limitations of smart meters and the privacy requirement of electricity usage data, theft detection has become a challenging task for electric utilities. To address this problem, a Distributed Intelligent Framework for Electricity Theft Detection (DIFETD) is proposed and implemented in this paper. It is equipped with Benford's Analysis for initial but powerful diagnostics on smart meter big data. A Stackelberg game-theoretic model is formulated to analyze the strategic interactions between one utility and multiple electricity thieves, which is applied to data flagged suspicious by Benford's Analysis. The Stackelberg equilibrium provides sampling rate and threshold to conduct a Likelihood Ratio Test (LRT) to detect potentially fraudulent meters. The framework is validated on real interval electricity usage data from an electric utility in Florida to filter fraudulent meters in a community.

AB - Electricity theft is a major contributor of nontechnical losses in the distribution systems of the smart grid. However, owing to the resource-limitations of smart meters and the privacy requirement of electricity usage data, theft detection has become a challenging task for electric utilities. To address this problem, a Distributed Intelligent Framework for Electricity Theft Detection (DIFETD) is proposed and implemented in this paper. It is equipped with Benford's Analysis for initial but powerful diagnostics on smart meter big data. A Stackelberg game-theoretic model is formulated to analyze the strategic interactions between one utility and multiple electricity thieves, which is applied to data flagged suspicious by Benford's Analysis. The Stackelberg equilibrium provides sampling rate and threshold to conduct a Likelihood Ratio Test (LRT) to detect potentially fraudulent meters. The framework is validated on real interval electricity usage data from an electric utility in Florida to filter fraudulent meters in a community.

KW - Benford's Analysis

KW - Likelihood Ratio Test

KW - Stackelberg game

KW - electricity theft

KW - smart meter

UR - http://www.scopus.com/inward/record.url?scp=85040217918&partnerID=8YFLogxK

U2 - 10.1109/RWEEK.2017.8088640

DO - 10.1109/RWEEK.2017.8088640

M3 - Conference contribution

AN - SCOPUS:85040217918

T3 - Proceedings - 2017 Resilience Week, RWS 2017

SP - 5

EP - 11

BT - Proceedings - 2017 Resilience Week, RWS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 Resilience Week, RWS 2017

Y2 - 18 September 2017 through 22 September 2017

ER -

Wei L, Sundararajan A, Sarwat AI, Biswas S, Ibrahim E. A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game. In Proceedings - 2017 Resilience Week, RWS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 5-11. 8088640. (Proceedings - 2017 Resilience Week, RWS 2017). doi: 10.1109/RWEEK.2017.8088640

A distributed intelligent framework for electricity theft detection using benford's law and stackelberg game

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this