Cyber-Physical Attack Conduction and Detection in Decentralized Power Systems

Mostafa Mohammadpourfard; Yang Weng; Abdullah Khalili; Istemihan Genc; Alireza Shefaei; Behnam Mohammadi-Ivatloo

doi:10.1109/ACCESS.2022.3151907

Cyber-Physical Attack Conduction and Detection in Decentralized Power Systems

Mostafa Mohammadpourfard^*
, Yang Weng
, Abdullah Khalili
, Istemihan Genc
, Alireza Shefaei
, Behnam Mohammadi-Ivatloo

^*Corresponding author for this work

Department of Electrical Engineering

Istanbul Technical University
Sahand University of Technology
Arizona State University
Hormozgan University
University of Tabriz
Delft University of Technology
Mugla Sıtkı Kocman University

Research output: Contribution to journal › Article › peer-review

20 Citations (Scopus)

Abstract

The expansion of power systems over large geographical areas renders centralized processing inefficient. Therefore, the distributed operation is increasingly adopted. This work introduces a new type of attack against distributed state estimation of power systems, which operates on inter-area boundary buses. We show that the developed attack can circumvent existing robust state estimators and the convergence-based detection approaches. Afterward, we carefully design a deep learning-based cyber-anomaly detection mechanism to detect such attacks. Simulations conducted on the IEEE 14-bus system reveal that the developed framework can obtain a very high detection accuracy. Moreover, experimental results indicate that the proposed detector surpasses current machine learning-based detection methods.

Original language	English
Pages (from-to)	29277-29286
Number of pages	10
Journal	IEEE Access
Volume	10
DOIs	https://doi.org/10.1109/ACCESS.2022.3151907
Publication status	Published - 2022

Bibliographical note

Publisher Copyright:
© 2013 IEEE.

Funding

This work was supported by the TÜBITAK and European Commission Horizon 2020 Marie Skłodowska-Curie Actions Co-Fund Program under Project 120C080.

Funders	Funder number
European Commission Horizon 2020 Marie Skłodowska-Curie Actions	120C080
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

Deep learning
cyber-attacks
distributed state estimation
smart grids

Access to Document

10.1109/ACCESS.2022.3151907

Cite this

@article{5e839c329b494f3992652e0402544b96,

title = "Cyber-Physical Attack Conduction and Detection in Decentralized Power Systems",

abstract = "The expansion of power systems over large geographical areas renders centralized processing inefficient. Therefore, the distributed operation is increasingly adopted. This work introduces a new type of attack against distributed state estimation of power systems, which operates on inter-area boundary buses. We show that the developed attack can circumvent existing robust state estimators and the convergence-based detection approaches. Afterward, we carefully design a deep learning-based cyber-anomaly detection mechanism to detect such attacks. Simulations conducted on the IEEE 14-bus system reveal that the developed framework can obtain a very high detection accuracy. Moreover, experimental results indicate that the proposed detector surpasses current machine learning-based detection methods.",

keywords = "Deep learning, cyber-attacks, distributed state estimation, smart grids",

author = "Mostafa Mohammadpourfard and Yang Weng and Abdullah Khalili and Istemihan Genc and Alireza Shefaei and Behnam Mohammadi-Ivatloo",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2022",

doi = "10.1109/ACCESS.2022.3151907",

language = "English",

volume = "10",

pages = "29277--29286",

journal = "IEEE Access",

issn = "2169-3536",

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

}

TY - JOUR

T1 - Cyber-Physical Attack Conduction and Detection in Decentralized Power Systems

AU - Mohammadpourfard, Mostafa

AU - Weng, Yang

AU - Khalili, Abdullah

AU - Genc, Istemihan

AU - Shefaei, Alireza

AU - Mohammadi-Ivatloo, Behnam

PY - 2022

Y1 - 2022

N2 - The expansion of power systems over large geographical areas renders centralized processing inefficient. Therefore, the distributed operation is increasingly adopted. This work introduces a new type of attack against distributed state estimation of power systems, which operates on inter-area boundary buses. We show that the developed attack can circumvent existing robust state estimators and the convergence-based detection approaches. Afterward, we carefully design a deep learning-based cyber-anomaly detection mechanism to detect such attacks. Simulations conducted on the IEEE 14-bus system reveal that the developed framework can obtain a very high detection accuracy. Moreover, experimental results indicate that the proposed detector surpasses current machine learning-based detection methods.

AB - The expansion of power systems over large geographical areas renders centralized processing inefficient. Therefore, the distributed operation is increasingly adopted. This work introduces a new type of attack against distributed state estimation of power systems, which operates on inter-area boundary buses. We show that the developed attack can circumvent existing robust state estimators and the convergence-based detection approaches. Afterward, we carefully design a deep learning-based cyber-anomaly detection mechanism to detect such attacks. Simulations conducted on the IEEE 14-bus system reveal that the developed framework can obtain a very high detection accuracy. Moreover, experimental results indicate that the proposed detector surpasses current machine learning-based detection methods.

KW - Deep learning

KW - cyber-attacks

KW - distributed state estimation

KW - smart grids

UR - https://www.scopus.com/pages/publications/85124817182

U2 - 10.1109/ACCESS.2022.3151907

DO - 10.1109/ACCESS.2022.3151907

M3 - Article

AN - SCOPUS:85124817182

SN - 2169-3536

VL - 10

SP - 29277

EP - 29286

JO - IEEE Access

JF - IEEE Access

ER -

Cyber-Physical Attack Conduction and Detection in Decentralized Power Systems

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this