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

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

5 Citations (Scopus)

22 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID)
Number of pages	6
Publisher	IEEE Press
Publication date	Nov 2021
Pages	1-6
Article number	9662148
ISBN (Print)	978-1-6654-4980-9
ISBN (Electronic)	978-1-6654-4979-3
DOIs	https://doi.org/10.1109/eGRID52793.2021.9662148
Publication status	Published - Nov 2021
Event	2021 6th IEEE Workshop on the Electronic Grid (eGRID) - New Orleans, LA, United States Duration: 8 Nov 2021 → 10 Nov 2021

Conference

Conference	2021 6th IEEE Workshop on the Electronic Grid (eGRID)
Country/Territory	United States
City	New Orleans, LA
Period	08/11/2021 → 10/11/2021

Keywords

Machine Learning
Power Electronics
Anomaly Detection
Physics-informed techniques
Cyber-Physical Systems
Cyber Attacks
Faults
Power Systems

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/eGRID52793.2021.9662148

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@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. in Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID)., 9662148, IEEE Press, pp. 1-6, 2021 6th IEEE Workshop on the Electronic Grid (eGRID), New Orleans, LA, United States, 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 et al.
Proceedings of the 2021 6th IEEE Workshop on the Electronic Grid (eGRID). IEEE Press, 2021. p. 1-6 9662148.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › 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

Abstract

Conference

Keywords

UN SDGs

Access to Document

AUB Link

Other files and links

Fingerprint

REPEPS: REliable Power Electronic based Power System

Cite this

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

Abstract

Conference

Keywords

UN SDGs

Access to Document

AUB Link

Other files and links

Fingerprint

Projects

REPEPS: REliable Power Electronic based Power System

Cite this