Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters

Mahmoud Nabil, Muhammad Ismail Muhammad, Mohamed Mahmoud, Mostafa Shahin, Khalid Qaraqe, Erchin Serpedin

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

2 Citations (Scopus)

Abstract

Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft detectors, this paper proposes a generalized deep recurrent neural network (RNN)-based electricity theft detector that can effectively thwart these cyberattacks. The proposed model exploits the time series nature of the customers' electricity consumption to implement a gated recurrent unit (GRU)-RNN, hence, improving the detection performance. In addition, the proposed RNN-based detector adopts a random search analysis in its learning stage to appropriately fine-tune its hyper-parameters. Extensive test studies are carried out to investigate the detector's performance using publicly available real data of 107,200 energy consumption days from 200 customers. Simulation results demonstrate the superior performance of the proposed detector compared with state-of-the-art electricity theft detectors.

Original languageEnglish
Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages740-745
Number of pages6
Volume2018-August
ISBN (Electronic)9781538637883
DOIs
Publication statusPublished - 26 Nov 2018
Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
Duration: 20 Aug 201824 Aug 2018

Other

Other24th International Conference on Pattern Recognition, ICPR 2018
CountryChina
CityBeijing
Period20/8/1824/8/18

Fingerprint

Advanced metering infrastructures
Electricity
Tuning
Detectors
Recurrent neural networks
Time series
Energy utilization
Monitoring

Keywords

  • AMI networks
  • cyberattacks
  • deep machine learning
  • Electricity theft detection

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Nabil, M., Muhammad, M. I., Mahmoud, M., Shahin, M., Qaraqe, K., & Serpedin, E. (2018). Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters. In 2018 24th International Conference on Pattern Recognition, ICPR 2018 (Vol. 2018-August, pp. 740-745). [8545748] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8545748

Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters. / Nabil, Mahmoud; Muhammad, Muhammad Ismail; Mahmoud, Mohamed; Shahin, Mostafa; Qaraqe, Khalid; Serpedin, Erchin.

2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. p. 740-745 8545748.

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

Nabil, M, Muhammad, MI, Mahmoud, M, Shahin, M, Qaraqe, K & Serpedin, E 2018, Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters. in 2018 24th International Conference on Pattern Recognition, ICPR 2018. vol. 2018-August, 8545748, Institute of Electrical and Electronics Engineers Inc., pp. 740-745, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, 20/8/18. https://doi.org/10.1109/ICPR.2018.8545748
Nabil M, Muhammad MI, Mahmoud M, Shahin M, Qaraqe K, Serpedin E. Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters. In 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August. Institute of Electrical and Electronics Engineers Inc. 2018. p. 740-745. 8545748 https://doi.org/10.1109/ICPR.2018.8545748
Nabil, Mahmoud ; Muhammad, Muhammad Ismail ; Mahmoud, Mohamed ; Shahin, Mostafa ; Qaraqe, Khalid ; Serpedin, Erchin. / Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters. 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. pp. 740-745
@inproceedings{35e5c29e37b64f6bb6fe4e9bcfccfc3e,
title = "Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters",
abstract = "Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft detectors, this paper proposes a generalized deep recurrent neural network (RNN)-based electricity theft detector that can effectively thwart these cyberattacks. The proposed model exploits the time series nature of the customers' electricity consumption to implement a gated recurrent unit (GRU)-RNN, hence, improving the detection performance. In addition, the proposed RNN-based detector adopts a random search analysis in its learning stage to appropriately fine-tune its hyper-parameters. Extensive test studies are carried out to investigate the detector's performance using publicly available real data of 107,200 energy consumption days from 200 customers. Simulation results demonstrate the superior performance of the proposed detector compared with state-of-the-art electricity theft detectors.",
keywords = "AMI networks, cyberattacks, deep machine learning, Electricity theft detection",
author = "Mahmoud Nabil and Muhammad, {Muhammad Ismail} and Mohamed Mahmoud and Mostafa Shahin and Khalid Qaraqe and Erchin Serpedin",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/ICPR.2018.8545748",
language = "English",
volume = "2018-August",
pages = "740--745",
booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters

AU - Nabil, Mahmoud

AU - Muhammad, Muhammad Ismail

AU - Mahmoud, Mohamed

AU - Shahin, Mostafa

AU - Qaraqe, Khalid

AU - Serpedin, Erchin

PY - 2018/11/26

Y1 - 2018/11/26

N2 - Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft detectors, this paper proposes a generalized deep recurrent neural network (RNN)-based electricity theft detector that can effectively thwart these cyberattacks. The proposed model exploits the time series nature of the customers' electricity consumption to implement a gated recurrent unit (GRU)-RNN, hence, improving the detection performance. In addition, the proposed RNN-based detector adopts a random search analysis in its learning stage to appropriately fine-tune its hyper-parameters. Extensive test studies are carried out to investigate the detector's performance using publicly available real data of 107,200 energy consumption days from 200 customers. Simulation results demonstrate the superior performance of the proposed detector compared with state-of-the-art electricity theft detectors.

AB - Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft detectors, this paper proposes a generalized deep recurrent neural network (RNN)-based electricity theft detector that can effectively thwart these cyberattacks. The proposed model exploits the time series nature of the customers' electricity consumption to implement a gated recurrent unit (GRU)-RNN, hence, improving the detection performance. In addition, the proposed RNN-based detector adopts a random search analysis in its learning stage to appropriately fine-tune its hyper-parameters. Extensive test studies are carried out to investigate the detector's performance using publicly available real data of 107,200 energy consumption days from 200 customers. Simulation results demonstrate the superior performance of the proposed detector compared with state-of-the-art electricity theft detectors.

KW - AMI networks

KW - cyberattacks

KW - deep machine learning

KW - Electricity theft detection

UR - http://www.scopus.com/inward/record.url?scp=85059766046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059766046&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2018.8545748

DO - 10.1109/ICPR.2018.8545748

M3 - Conference contribution

AN - SCOPUS:85059766046

VL - 2018-August

SP - 740

EP - 745

BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -