Physics Guided Data-Driven Characterization of Anomalies in Power Electronic Systems

Kaustubh Bhatnagar; Subham Sahoo; Florin Iov; Frede Blaabjerg

doi:10.1109/eGRID52793.2021.9662148

Physics Guided Data-Driven Characterization of Anomalies in Power Electronic Systems

Kaustubh Bhatnagar^*, Subham Sahoo, Florin Iov, Frede Blaabjerg

^*Kontaktforfatter

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

22 Downloads (Pure)

Abstrakt

The transition of conventional power system onto power electronics dominated grid (PEDG) has lead to amplified complexity in system-level control schemes to maintain reliability and operational stability. Considering the abundance of data in PEDG, machine learning (ML) schemes have emerged as a promising alternative. In this article, a physical guided data-driven approach using pattern recognition neural network (PRNN) is employed with semi-supervised learning. To distinguish between the faults and cyber-attacks without relying historical data scenarios. Finally, the results of proposed approach are discussed by utilizing ML tools.

Originalsprog	Engelsk
Titel	Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID)
Antal sider	6
Forlag	IEEE Press
Publikationsdato	nov. 2021
Sider	1-6
Artikelnummer	9662148
ISBN (Trykt)	978-1-6654-4980-9
ISBN (Elektronisk)	978-1-6654-4979-3
DOI	https://doi.org/10.1109/eGRID52793.2021.9662148
Status	Udgivet - nov. 2021
Begivenhed	2021 6th IEEE Workshop on the Electronic Grid (eGRID) - New Orleans, LA, USA Varighed: 8 nov. 2021 → 10 nov. 2021

Konference

Konference	2021 6th IEEE Workshop on the Electronic Grid (eGRID)
Land/Område	USA
By	New Orleans, LA
Periode	08/11/2021 → 10/11/2021

FN’s Verdensmål

Denne publikation bidrager til følgende verdensmål

Adgang til dokumentet

10.1109/eGRID52793.2021.9662148

Andre filer og links

Link to publication in Scopus

1 Igangværende

REPEPS: REliable Power Electronic based Power System
Blaabjerg, F., Iannuzzo, F., Davari, P., Wang, H., Wang, X. & Yang, Y.
01/08/2017 → 01/12/2023
Projekter: Projekt › Forskning

Citationsformater

@inproceedings{03c5bdcbd9924d1ba82c674b986f2c1e,

title = "Physics Guided Data-Driven Characterization of Anomalies in Power Electronic Systems",

abstract = "The transition of conventional power system onto power electronics dominated grid (PEDG) has lead to amplified complexity in system-level control schemes to maintain reliability and operational stability. Considering the abundance of data in PEDG, machine learning (ML) schemes have emerged as a promising alternative. In this article, a physical guided data-driven approach using pattern recognition neural network (PRNN) is employed with semi-supervised learning. To distinguish between the faults and cyber-attacks without relying historical data scenarios. Finally, the results of proposed approach are discussed by utilizing ML tools.",

keywords = "Machine Learning, Power Electronics, Anomaly Detection, Physics-informed techniques, Cyber-Physical Systems, Cyber Attacks, Faults, Power Systems",

author = "Kaustubh Bhatnagar and Subham Sahoo and Florin Iov and Frede Blaabjerg",

year = "2021",

month = nov,

doi = "10.1109/eGRID52793.2021.9662148",

language = "English",

isbn = "978-1-6654-4980-9",

pages = "1--6",

booktitle = "Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID)",

publisher = "IEEE Press",

note = "2021 6th IEEE Workshop on the Electronic Grid (eGRID), eGrid ; Conference date: 08-11-2021 Through 10-11-2021",

}

Bhatnagar, K , Sahoo, S , Iov, F & Blaabjerg, F 2021, Physics Guided Data-Driven Characterization of Anomalies in Power Electronic Systems. i Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID)., 9662148, IEEE Press, s. 1-6, 2021 6th IEEE Workshop on the Electronic Grid (eGRID), New Orleans, LA, USA, 08/11/2021. https://doi.org/10.1109/eGRID52793.2021.9662148

Physics Guided Data-Driven Characterization of Anomalies in Power Electronic Systems. / Bhatnagar, Kaustubh ; Sahoo, Subham ; Iov, Florin ; Blaabjerg, Frede.

Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID). IEEE Press, 2021. s. 1-6 9662148.

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Physics Guided Data-Driven Characterization of Anomalies in Power Electronic Systems

AU - Bhatnagar, Kaustubh

AU - Sahoo, Subham

AU - Iov, Florin

AU - Blaabjerg, Frede

PY - 2021/11

Y1 - 2021/11

N2 - The transition of conventional power system onto power electronics dominated grid (PEDG) has lead to amplified complexity in system-level control schemes to maintain reliability and operational stability. Considering the abundance of data in PEDG, machine learning (ML) schemes have emerged as a promising alternative. In this article, a physical guided data-driven approach using pattern recognition neural network (PRNN) is employed with semi-supervised learning. To distinguish between the faults and cyber-attacks without relying historical data scenarios. Finally, the results of proposed approach are discussed by utilizing ML tools.

AB - The transition of conventional power system onto power electronics dominated grid (PEDG) has lead to amplified complexity in system-level control schemes to maintain reliability and operational stability. Considering the abundance of data in PEDG, machine learning (ML) schemes have emerged as a promising alternative. In this article, a physical guided data-driven approach using pattern recognition neural network (PRNN) is employed with semi-supervised learning. To distinguish between the faults and cyber-attacks without relying historical data scenarios. Finally, the results of proposed approach are discussed by utilizing ML tools.

KW - Machine Learning

KW - Power Electronics

KW - Anomaly Detection

KW - Physics-informed techniques

KW - Cyber-Physical Systems

KW - Cyber Attacks

KW - Faults

KW - Power Systems

UR - http://www.scopus.com/inward/record.url?scp=85125009504&partnerID=8YFLogxK

U2 - 10.1109/eGRID52793.2021.9662148

DO - 10.1109/eGRID52793.2021.9662148

M3 - Article in proceeding

SN - 978-1-6654-4980-9

SP - 1

EP - 6

BT - Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID)

PB - IEEE Press

T2 - 2021 6th IEEE Workshop on the Electronic Grid (eGRID)

Y2 - 8 November 2021 through 10 November 2021

ER -

Physics Guided Data-Driven Characterization of Anomalies in Power Electronic Systems

Abstrakt

Konference

FN’s Verdensmål

Adgang til dokumentet

Andre filer og links

Fingeraftryk

Projekter

REPEPS: REliable Power Electronic based Power System

Citationsformater