An Efficient Machine Learning Model for Microgrid Fault Detection and Classification: Protection Approach

Mohammed Alsaba; Mohammad Abido

doi:10.1109/PESGM52003.2023.10252224

An Efficient Machine Learning Model for Microgrid Fault Detection and Classification: Protection Approach

Mohammed Alsaba^*
, Mohammad Abido

^*Corresponding author for this work

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

5 Scopus citations

Abstract

The protection system is an important component of microgrid operation and stability. The protection system must be capable of identifying faults, isolating the faulty sections, and ensuring continuity of the power supply to unaffected loads. The objective of this paper is to develop an efficient machine-learning fault detection and classification protection device capable of detecting low and high-impedance faults in AC microgrids. The protection device shall be adaptive to microgrid topology changes, bidirectional power flow, fault current levels, renewable energy resources faults infeed, stable under normal conditions, and fast tripping for low and high impedance faults. The protection device is a hybrid deep CNN-GRU-directional relay model. The paper adopts a protection approach for accuracy, stability against reverse direction faults, and noise immunity when evaluating this efficient model along with other machine learning models using MATLAB.

Original language	English
Title of host publication	2023 IEEE Power and Energy Society General Meeting, PESGM 2023
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665464413
DOIs	https://doi.org/10.1109/PESGM52003.2023.10252224
State	Published - 2023
Event	2023 IEEE Power and Energy Society General Meeting, PESGM 2023 - Orlando, United States Duration: 16 Jul 2023 → 20 Jul 2023

Publication series

Name	IEEE Power and Energy Society General Meeting
Volume	2023-July
ISSN (Print)	1944-9925
ISSN (Electronic)	1944-9933

Conference

Conference	2023 IEEE Power and Energy Society General Meeting, PESGM 2023
Country/Territory	United States
City	Orlando
Period	16/07/23 → 20/07/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

machine learning
microgrids
power system protection

ASJC Scopus subject areas

Energy Engineering and Power Technology
Nuclear Energy and Engineering
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering

UN SDGs

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

Access to Document

10.1109/PESGM52003.2023.10252224

Cite this

@inproceedings{b2f32c0a59164ecfbb9c30bbf8960456,

title = "An Efficient Machine Learning Model for Microgrid Fault Detection and Classification: Protection Approach",

abstract = "The protection system is an important component of microgrid operation and stability. The protection system must be capable of identifying faults, isolating the faulty sections, and ensuring continuity of the power supply to unaffected loads. The objective of this paper is to develop an efficient machine-learning fault detection and classification protection device capable of detecting low and high-impedance faults in AC microgrids. The protection device shall be adaptive to microgrid topology changes, bidirectional power flow, fault current levels, renewable energy resources faults infeed, stable under normal conditions, and fast tripping for low and high impedance faults. The protection device is a hybrid deep CNN-GRU-directional relay model. The paper adopts a protection approach for accuracy, stability against reverse direction faults, and noise immunity when evaluating this efficient model along with other machine learning models using MATLAB.",

keywords = "machine learning, microgrids, power system protection",

author = "Mohammed Alsaba and Mohammad Abido",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Power and Energy Society General Meeting, PESGM 2023 ; Conference date: 16-07-2023 Through 20-07-2023",

year = "2023",

doi = "10.1109/PESGM52003.2023.10252224",

language = "English",

series = "IEEE Power and Energy Society General Meeting",

publisher = "IEEE Computer Society",

booktitle = "2023 IEEE Power and Energy Society General Meeting, PESGM 2023",

address = "United States",

}

Alsaba, M & Abido, M 2023, An Efficient Machine Learning Model for Microgrid Fault Detection and Classification: Protection Approach. in 2023 IEEE Power and Energy Society General Meeting, PESGM 2023. IEEE Power and Energy Society General Meeting, vol. 2023-July, IEEE Computer Society, 2023 IEEE Power and Energy Society General Meeting, PESGM 2023, Orlando, United States, 16/07/23. https://doi.org/10.1109/PESGM52003.2023.10252224

An Efficient Machine Learning Model for Microgrid Fault Detection and Classification: Protection Approach. / Alsaba, Mohammed; Abido, Mohammad.
2023 IEEE Power and Energy Society General Meeting, PESGM 2023. IEEE Computer Society, 2023. (IEEE Power and Energy Society General Meeting; Vol. 2023-July).

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

TY - GEN

T1 - An Efficient Machine Learning Model for Microgrid Fault Detection and Classification

T2 - 2023 IEEE Power and Energy Society General Meeting, PESGM 2023

AU - Alsaba, Mohammed

AU - Abido, Mohammad

PY - 2023

Y1 - 2023

N2 - The protection system is an important component of microgrid operation and stability. The protection system must be capable of identifying faults, isolating the faulty sections, and ensuring continuity of the power supply to unaffected loads. The objective of this paper is to develop an efficient machine-learning fault detection and classification protection device capable of detecting low and high-impedance faults in AC microgrids. The protection device shall be adaptive to microgrid topology changes, bidirectional power flow, fault current levels, renewable energy resources faults infeed, stable under normal conditions, and fast tripping for low and high impedance faults. The protection device is a hybrid deep CNN-GRU-directional relay model. The paper adopts a protection approach for accuracy, stability against reverse direction faults, and noise immunity when evaluating this efficient model along with other machine learning models using MATLAB.

AB - The protection system is an important component of microgrid operation and stability. The protection system must be capable of identifying faults, isolating the faulty sections, and ensuring continuity of the power supply to unaffected loads. The objective of this paper is to develop an efficient machine-learning fault detection and classification protection device capable of detecting low and high-impedance faults in AC microgrids. The protection device shall be adaptive to microgrid topology changes, bidirectional power flow, fault current levels, renewable energy resources faults infeed, stable under normal conditions, and fast tripping for low and high impedance faults. The protection device is a hybrid deep CNN-GRU-directional relay model. The paper adopts a protection approach for accuracy, stability against reverse direction faults, and noise immunity when evaluating this efficient model along with other machine learning models using MATLAB.

KW - machine learning

KW - microgrids

KW - power system protection

UR - https://www.scopus.com/pages/publications/85174682320

U2 - 10.1109/PESGM52003.2023.10252224

DO - 10.1109/PESGM52003.2023.10252224

M3 - Conference contribution

AN - SCOPUS:85174682320

T3 - IEEE Power and Energy Society General Meeting

BT - 2023 IEEE Power and Energy Society General Meeting, PESGM 2023

PB - IEEE Computer Society

Y2 - 16 July 2023 through 20 July 2023

ER -

An Efficient Machine Learning Model for Microgrid Fault Detection and Classification: Protection Approach

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this