Arcing Fault Detection with Interpretable Learning Model under the Integration of Renewable Energy

Yousaf Hashmy; Qiushi Cui; Zhihao Ma; Yang Weng

doi:10.1109/NAPS46351.2019.8999972

Arcing Fault Detection with Interpretable Learning Model under the Integration of Renewable Energy

Yousaf Hashmy, Qiushi Cui, Zhihao Ma, Yang Weng

Engineering, Ira A. Fulton Schools of (IAFSE)

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

Abstract

Under the trend of deeper renewable energy integration, active distribution networks are facing increasing uncertainty and security issues, among which the arcing fault detection (AFD) has baffled researchers for years. Existing machine learning based AFD methods are deficient in feature extraction and model interpretability. To overcome these limitations in learning algorithms, we have designed a way to translate the non-transparent machine learning prediction model into an implementable logic for AFD. Moreover, the AFD logic is tested under different fault scenarios and realistic renewable generation data, with the help of our self-developed AFD software. The performance from various tests shows that the interpretable prediction model has high accuracy, dependability, security and speed under the integration of renewable energy.

Original language	English (US)
Title of host publication	51st North American Power Symposium, NAPS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728104072
DOIs	https://doi.org/10.1109/NAPS46351.2019.8999972
State	Published - Oct 2019
Event	51st North American Power Symposium, NAPS 2019 - Wichita, United States Duration: Oct 13 2019 → Oct 15 2019

Publication series

Name	51st North American Power Symposium, NAPS 2019

Conference

Conference	51st North American Power Symposium, NAPS 2019
Country/Territory	United States
City	Wichita
Period	10/13/19 → 10/15/19

Keywords

Arcing Fault Detection
Distribution Networks
Power System Protection
Renewable Energy

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality

Access to Document

10.1109/NAPS46351.2019.8999972

Cite this

Arcing Fault Detection with Interpretable Learning Model under the Integration of Renewable Energy. / Hashmy, Yousaf; Cui, Qiushi; Ma, Zhihao et al.
51st North American Power Symposium, NAPS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8999972 (51st North American Power Symposium, NAPS 2019).

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

Hashmy, Y, Cui, Q, Ma, Z & Weng, Y 2019, Arcing Fault Detection with Interpretable Learning Model under the Integration of Renewable Energy. in 51st North American Power Symposium, NAPS 2019., 8999972, 51st North American Power Symposium, NAPS 2019, Institute of Electrical and Electronics Engineers Inc., 51st North American Power Symposium, NAPS 2019, Wichita, United States, 10/13/19. https://doi.org/10.1109/NAPS46351.2019.8999972

@inproceedings{abdbddbcd2034ea9a8164bb43f647848,

title = "Arcing Fault Detection with Interpretable Learning Model under the Integration of Renewable Energy",

abstract = "Under the trend of deeper renewable energy integration, active distribution networks are facing increasing uncertainty and security issues, among which the arcing fault detection (AFD) has baffled researchers for years. Existing machine learning based AFD methods are deficient in feature extraction and model interpretability. To overcome these limitations in learning algorithms, we have designed a way to translate the non-transparent machine learning prediction model into an implementable logic for AFD. Moreover, the AFD logic is tested under different fault scenarios and realistic renewable generation data, with the help of our self-developed AFD software. The performance from various tests shows that the interpretable prediction model has high accuracy, dependability, security and speed under the integration of renewable energy.",

keywords = "Arcing Fault Detection, Distribution Networks, Power System Protection, Renewable Energy",

author = "Yousaf Hashmy and Qiushi Cui and Zhihao Ma and Yang Weng",

year = "2019",

month = oct,

doi = "10.1109/NAPS46351.2019.8999972",

language = "English (US)",

series = "51st North American Power Symposium, NAPS 2019",

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

booktitle = "51st North American Power Symposium, NAPS 2019",

note = "51st North American Power Symposium, NAPS 2019 ; Conference date: 13-10-2019 Through 15-10-2019",

}

TY - GEN

T1 - Arcing Fault Detection with Interpretable Learning Model under the Integration of Renewable Energy

AU - Hashmy, Yousaf

AU - Cui, Qiushi

AU - Ma, Zhihao

AU - Weng, Yang

PY - 2019/10

Y1 - 2019/10

N2 - Under the trend of deeper renewable energy integration, active distribution networks are facing increasing uncertainty and security issues, among which the arcing fault detection (AFD) has baffled researchers for years. Existing machine learning based AFD methods are deficient in feature extraction and model interpretability. To overcome these limitations in learning algorithms, we have designed a way to translate the non-transparent machine learning prediction model into an implementable logic for AFD. Moreover, the AFD logic is tested under different fault scenarios and realistic renewable generation data, with the help of our self-developed AFD software. The performance from various tests shows that the interpretable prediction model has high accuracy, dependability, security and speed under the integration of renewable energy.

AB - Under the trend of deeper renewable energy integration, active distribution networks are facing increasing uncertainty and security issues, among which the arcing fault detection (AFD) has baffled researchers for years. Existing machine learning based AFD methods are deficient in feature extraction and model interpretability. To overcome these limitations in learning algorithms, we have designed a way to translate the non-transparent machine learning prediction model into an implementable logic for AFD. Moreover, the AFD logic is tested under different fault scenarios and realistic renewable generation data, with the help of our self-developed AFD software. The performance from various tests shows that the interpretable prediction model has high accuracy, dependability, security and speed under the integration of renewable energy.

KW - Arcing Fault Detection

KW - Distribution Networks

KW - Power System Protection

KW - Renewable Energy

UR - http://www.scopus.com/inward/record.url?scp=85080874348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85080874348&partnerID=8YFLogxK

U2 - 10.1109/NAPS46351.2019.8999972

DO - 10.1109/NAPS46351.2019.8999972

M3 - Conference contribution

T3 - 51st North American Power Symposium, NAPS 2019

BT - 51st North American Power Symposium, NAPS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 51st North American Power Symposium, NAPS 2019

Y2 - 13 October 2019 through 15 October 2019

ER -

Arcing Fault Detection with Interpretable Learning Model under the Integration of Renewable Energy

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this