Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain

<p dir="ltr">In this article, we investigate the problem of electricity theft attacks on smart meters when malicious customers (i.e., adversaries) claim injecting more generated energy into the grid to get more profits from utility companies. These attacks can be applied by accessing...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Maymouna Ez Eddin (16904604) (author)
مؤلفون آخرون: Abdullatif Albaseer (16904607) (author), Mohamed Abdallah (3073191) (author), Sertac Bayhan (16388511) (author), Marwa K. Qaraqe (8115020) (author), Saif Al-Kuwari (16904610) (author), Haitham Abu-Rub (16855500) (author)
منشور في: 2022
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513560904728576
author Maymouna Ez Eddin (16904604)
author2 Abdullatif Albaseer (16904607)
Mohamed Abdallah (3073191)
Sertac Bayhan (16388511)
Marwa K. Qaraqe (8115020)
Saif Al-Kuwari (16904610)
Haitham Abu-Rub (16855500)
author2_role author
author
author
author
author
author
author_facet Maymouna Ez Eddin (16904604)
Abdullatif Albaseer (16904607)
Mohamed Abdallah (3073191)
Sertac Bayhan (16388511)
Marwa K. Qaraqe (8115020)
Saif Al-Kuwari (16904610)
Haitham Abu-Rub (16855500)
author_role author
dc.creator.none.fl_str_mv Maymouna Ez Eddin (16904604)
Abdullatif Albaseer (16904607)
Mohamed Abdallah (3073191)
Sertac Bayhan (16388511)
Marwa K. Qaraqe (8115020)
Saif Al-Kuwari (16904610)
Haitham Abu-Rub (16855500)
dc.date.none.fl_str_mv 2022-11-25T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/ojies.2022.3224784
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Fine-Tuned_RNN-Based_Detector_for_Electricity_Theft_Attacks_in_Smart_Grid_Generation_Domain/24056292
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Communications engineering
Electrical engineering
Information and computing sciences
Cybersecurity and privacy
Machine learning
Detectors
Smart meters
Anomaly detection
Perturbation methods
Meters
Fuels
Renewable energy sources
Smart grids
Deep learning
Cyberattacks on smart grid
Electricity theft
Generation domain
Deep-learning (DL)-based detector
Small perturbations
dc.title.none.fl_str_mv Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">In this article, we investigate the problem of electricity theft attacks on smart meters when malicious customers (i.e., adversaries) claim injecting more generated energy into the grid to get more profits from utility companies. These attacks can be applied by accessing the smart meters monitoring renewable-based distributed generation (DG), and manipulating the reading. In this article, we propose approaches that rely on data sources with only a single generator (i.e., solar only) and multifuel type; and address the crucial effects of slight perturbations that the attacker can add, which can deceive the detector. In particular, this article introduces an efficient multitask deep-learning-based detector that offers a higher detection rate, copes with different fuel types, and uses only single data sources. The proposed detector incorporates months and days as two additional features to boost the performance and properly guide the model to successful detection. The proposed method is then extended to consider small perturbations that attackers may use to launch successful attacks. We conduct extensive simulations for two different detectors, one for solar DG and the other for multiple fuel types (i.e., solar and wind). Using a realistic dataset, the results reveal that the proposed recurrent neural network-based detectors identify adversaries at a higher rate than the existing solutions, even with minimal perturbations and different fuel types.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Open Journal of the Industrial Electronics Society<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/ojies.2022.3224784" target="_blank">https://dx.doi.org/10.1109/ojies.2022.3224784</a></p>
eu_rights_str_mv openAccess
id Manara2_b53b660579a0080268e3dfe235f2557f
identifier_str_mv 10.1109/ojies.2022.3224784
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24056292
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation DomainMaymouna Ez Eddin (16904604)Abdullatif Albaseer (16904607)Mohamed Abdallah (3073191)Sertac Bayhan (16388511)Marwa K. Qaraqe (8115020)Saif Al-Kuwari (16904610)Haitham Abu-Rub (16855500)EngineeringCommunications engineeringElectrical engineeringInformation and computing sciencesCybersecurity and privacyMachine learningDetectorsSmart metersAnomaly detectionPerturbation methodsMetersFuelsRenewable energy sourcesSmart gridsDeep learningCyberattacks on smart gridElectricity theftGeneration domainDeep-learning (DL)-based detectorSmall perturbations<p dir="ltr">In this article, we investigate the problem of electricity theft attacks on smart meters when malicious customers (i.e., adversaries) claim injecting more generated energy into the grid to get more profits from utility companies. These attacks can be applied by accessing the smart meters monitoring renewable-based distributed generation (DG), and manipulating the reading. In this article, we propose approaches that rely on data sources with only a single generator (i.e., solar only) and multifuel type; and address the crucial effects of slight perturbations that the attacker can add, which can deceive the detector. In particular, this article introduces an efficient multitask deep-learning-based detector that offers a higher detection rate, copes with different fuel types, and uses only single data sources. The proposed detector incorporates months and days as two additional features to boost the performance and properly guide the model to successful detection. The proposed method is then extended to consider small perturbations that attackers may use to launch successful attacks. We conduct extensive simulations for two different detectors, one for solar DG and the other for multiple fuel types (i.e., solar and wind). Using a realistic dataset, the results reveal that the proposed recurrent neural network-based detectors identify adversaries at a higher rate than the existing solutions, even with minimal perturbations and different fuel types.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Open Journal of the Industrial Electronics Society<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/ojies.2022.3224784" target="_blank">https://dx.doi.org/10.1109/ojies.2022.3224784</a></p>2022-11-25T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/ojies.2022.3224784https://figshare.com/articles/journal_contribution/Fine-Tuned_RNN-Based_Detector_for_Electricity_Theft_Attacks_in_Smart_Grid_Generation_Domain/24056292CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240562922022-11-25T00:00:00Z
spellingShingle Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
Maymouna Ez Eddin (16904604)
Engineering
Communications engineering
Electrical engineering
Information and computing sciences
Cybersecurity and privacy
Machine learning
Detectors
Smart meters
Anomaly detection
Perturbation methods
Meters
Fuels
Renewable energy sources
Smart grids
Deep learning
Cyberattacks on smart grid
Electricity theft
Generation domain
Deep-learning (DL)-based detector
Small perturbations
status_str publishedVersion
title Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
title_full Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
title_fullStr Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
title_full_unstemmed Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
title_short Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
title_sort Fine-Tuned RNN-Based Detector for Electricity Theft Attacks in Smart Grid Generation Domain
topic Engineering
Communications engineering
Electrical engineering
Information and computing sciences
Cybersecurity and privacy
Machine learning
Detectors
Smart meters
Anomaly detection
Perturbation methods
Meters
Fuels
Renewable energy sources
Smart grids
Deep learning
Cyberattacks on smart grid
Electricity theft
Generation domain
Deep-learning (DL)-based detector
Small perturbations