Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids

Hamideh Alvand; Alireza Zare; Mohammad B. Shadmand; Haitham Abu-Rub

doi:10.1109/PECI57361.2023.10197837

Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids

Hamideh Alvand, Alireza Zare, Mohammad B. Shadmand, Haitham Abu-Rub

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

2 Citations (Scopus)

Abstract

This paper presents a Bayesian regularization based artificial neural network (BRANN) corrective actions for resilient operation of power electronic dominated grids (PEDG) with compromised sensors of grid-forming (GFM) or grid-following (GFL) inverters. GFM inverters play a significant role in governing the voltage and frequency stability of upcoming PEDG. Thus, spoofing the GFM inverter sensors' readings for their feedback control systems can jeopardize the PEDG resilient operation. This paper presents a framework that corrects the spoofed sensors' readings in the primary controller of the GFM inverter in PEDG. A neural network is trained via Bayesian regularization to realize the proposed corrective actions for sensors readings and consequently enhancing the resiliency of PEDG under sensor attacks. The trained neural network is integrated with GFM inverter's primary control loop to provide real-time corrective action whenever intrusive sensor behavior is detected. Summary of the proposed framework is provided in this paper. The simulated case studies are provided in the paper to validate the theoretical expectations.

Original language	English
Title of host publication	2023 IEEE Power and Energy Conference at Illinois, PECI 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350399400
DOIs	https://doi.org/10.1109/PECI57361.2023.10197837
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE Power and Energy Conference at Illinois, PECI 2023 - Champaign, United States Duration: 2 Mar 2023 → 3 Mar 2023

Publication series

Name	2023 IEEE Power and Energy Conference at Illinois, PECI 2023

Conference

Conference	2023 IEEE Power and Energy Conference at Illinois, PECI 2023
Country/Territory	United States
City	Champaign
Period	2/03/23 → 3/03/23

Keywords

Bayesian regularization
artificial neural network
corrective action
intrusion detection
power electronic dominated grid
resiliency
spoofing sensors
stability

Access to Document

10.1109/PECI57361.2023.10197837

Cite this

Alvand, H., Zare, A., Shadmand, M. B., & Abu-Rub, H. (2023). Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids. In 2023 IEEE Power and Energy Conference at Illinois, PECI 2023 (2023 IEEE Power and Energy Conference at Illinois, PECI 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PECI57361.2023.10197837

Alvand, Hamideh ; Zare, Alireza ; Shadmand, Mohammad B. et al. / Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids. 2023 IEEE Power and Energy Conference at Illinois, PECI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Power and Energy Conference at Illinois, PECI 2023).

@inproceedings{687cf7264bfc48cf92776ec4325a2e07,

title = "Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids",

abstract = "This paper presents a Bayesian regularization based artificial neural network (BRANN) corrective actions for resilient operation of power electronic dominated grids (PEDG) with compromised sensors of grid-forming (GFM) or grid-following (GFL) inverters. GFM inverters play a significant role in governing the voltage and frequency stability of upcoming PEDG. Thus, spoofing the GFM inverter sensors' readings for their feedback control systems can jeopardize the PEDG resilient operation. This paper presents a framework that corrects the spoofed sensors' readings in the primary controller of the GFM inverter in PEDG. A neural network is trained via Bayesian regularization to realize the proposed corrective actions for sensors readings and consequently enhancing the resiliency of PEDG under sensor attacks. The trained neural network is integrated with GFM inverter's primary control loop to provide real-time corrective action whenever intrusive sensor behavior is detected. Summary of the proposed framework is provided in this paper. The simulated case studies are provided in the paper to validate the theoretical expectations.",

keywords = "Bayesian regularization, artificial neural network, corrective action, intrusion detection, power electronic dominated grid, resiliency, spoofing sensors, stability",

author = "Hamideh Alvand and Alireza Zare and Shadmand, {Mohammad B.} and Haitham Abu-Rub",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Power and Energy Conference at Illinois, PECI 2023 ; Conference date: 02-03-2023 Through 03-03-2023",

year = "2023",

doi = "10.1109/PECI57361.2023.10197837",

language = "English",

series = "2023 IEEE Power and Energy Conference at Illinois, PECI 2023",

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

booktitle = "2023 IEEE Power and Energy Conference at Illinois, PECI 2023",

address = "United States",

}

Alvand, H, Zare, A, Shadmand, MB & Abu-Rub, H 2023, Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids. in 2023 IEEE Power and Energy Conference at Illinois, PECI 2023. 2023 IEEE Power and Energy Conference at Illinois, PECI 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Power and Energy Conference at Illinois, PECI 2023, Champaign, United States, 2/03/23. https://doi.org/10.1109/PECI57361.2023.10197837

Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids. / Alvand, Hamideh; Zare, Alireza; Shadmand, Mohammad B. et al.
2023 IEEE Power and Energy Conference at Illinois, PECI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Power and Energy Conference at Illinois, PECI 2023).

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

TY - GEN

T1 - Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids

AU - Alvand, Hamideh

AU - Zare, Alireza

AU - Shadmand, Mohammad B.

AU - Abu-Rub, Haitham

PY - 2023

Y1 - 2023

N2 - This paper presents a Bayesian regularization based artificial neural network (BRANN) corrective actions for resilient operation of power electronic dominated grids (PEDG) with compromised sensors of grid-forming (GFM) or grid-following (GFL) inverters. GFM inverters play a significant role in governing the voltage and frequency stability of upcoming PEDG. Thus, spoofing the GFM inverter sensors' readings for their feedback control systems can jeopardize the PEDG resilient operation. This paper presents a framework that corrects the spoofed sensors' readings in the primary controller of the GFM inverter in PEDG. A neural network is trained via Bayesian regularization to realize the proposed corrective actions for sensors readings and consequently enhancing the resiliency of PEDG under sensor attacks. The trained neural network is integrated with GFM inverter's primary control loop to provide real-time corrective action whenever intrusive sensor behavior is detected. Summary of the proposed framework is provided in this paper. The simulated case studies are provided in the paper to validate the theoretical expectations.

AB - This paper presents a Bayesian regularization based artificial neural network (BRANN) corrective actions for resilient operation of power electronic dominated grids (PEDG) with compromised sensors of grid-forming (GFM) or grid-following (GFL) inverters. GFM inverters play a significant role in governing the voltage and frequency stability of upcoming PEDG. Thus, spoofing the GFM inverter sensors' readings for their feedback control systems can jeopardize the PEDG resilient operation. This paper presents a framework that corrects the spoofed sensors' readings in the primary controller of the GFM inverter in PEDG. A neural network is trained via Bayesian regularization to realize the proposed corrective actions for sensors readings and consequently enhancing the resiliency of PEDG under sensor attacks. The trained neural network is integrated with GFM inverter's primary control loop to provide real-time corrective action whenever intrusive sensor behavior is detected. Summary of the proposed framework is provided in this paper. The simulated case studies are provided in the paper to validate the theoretical expectations.

KW - Bayesian regularization

KW - artificial neural network

KW - corrective action

KW - intrusion detection

KW - power electronic dominated grid

KW - resiliency

KW - spoofing sensors

KW - stability

UR - http://www.scopus.com/inward/record.url?scp=85169426931&partnerID=8YFLogxK

U2 - 10.1109/PECI57361.2023.10197837

DO - 10.1109/PECI57361.2023.10197837

M3 - Conference contribution

AN - SCOPUS:85169426931

T3 - 2023 IEEE Power and Energy Conference at Illinois, PECI 2023

BT - 2023 IEEE Power and Energy Conference at Illinois, PECI 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Power and Energy Conference at Illinois, PECI 2023

Y2 - 2 March 2023 through 3 March 2023

ER -

Alvand H, Zare A, Shadmand MB, Abu-Rub H. Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids. In 2023 IEEE Power and Energy Conference at Illinois, PECI 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE Power and Energy Conference at Illinois, PECI 2023). doi: 10.1109/PECI57361.2023.10197837

Data-Driven Based Corrective Actions and Detection of Intrusive Sensors Behavior in Power Electronic Dominated Grids

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this