Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources

Zhidi Lin; Dongliang Duan; Qi Yang; Xiang Cheng; Liuqing Yang; Shuguang Cui

doi:10.1109/iSPEC48194.2019.8974949

Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources

Zhidi Lin, Dongliang Duan, Qi Yang, Xiang Cheng, Liuqing Yang, Shuguang Cui

Electrical and Computer Engineering

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

Abstract

The integration of Distributed Energy Resources (DERs) introduces non-conventional two-way power flows which cannot be captured well by traditional model-based techniques. This brings great challenges to accurately localize faults and initiate correct actions of the protection system. In this paper, we propose a data-driven fault localization strategy based on multilevel system regionalization and probabilistic fault detections on all the subregions. The strategy combines the Support Vector Data Description (SVDD) and the Kernel Density Estimation (KDE) to provide the confidence level of fault detections in each subregion by p-values, and then accurately localize the fault by comparing the p-values. Our experiments show that the proposed data-driven fault localization can greatly increase the accuracy of fault localization for distribution systems with high integration of DERs.

Original language	English (US)
Title of host publication	iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference
Subtitle of host publication	Grid Modernization for Energy Revolution, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1021-1026
Number of pages	6
ISBN (Electronic)	9781728149301
DOIs	https://doi.org/10.1109/iSPEC48194.2019.8974949
State	Published - Nov 2019
Event	2019 IEEE Sustainable Power and Energy Conference, iSPEC 2019 - Beijing, China Duration: Nov 21 2019 → Nov 23 2019

Publication series

Name	iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings

Conference

Conference	2019 IEEE Sustainable Power and Energy Conference, iSPEC 2019
Country	China
City	Beijing
Period	11/21/19 → 11/23/19

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work was supported in part by Shenzhen Fundamental Research Fund under Grant No. JCYJ20170411102217994 and ZDSYS201707251409055, Shenzhen Peacock Plan under Grant KQTD2015033114415450 and Guangdong province “The Pearl River Talent Recruitment Program Innovative and Entrepreneurial Teams in 2017” – Data Driven Evolution of Future Intelligent Network Team under grant No. 2017ZT07X152.

Keywords

Distributed Energy Resources (DERs)
Support Vector Data Description (SVDD)
distribution systems
fault localization
probabilistic fault detection

Access

10.1109/iSPEC48194.2019.8974949

Fingerprint Dive into the research topics of 'Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources'. Together they form a unique fingerprint.

Cite this

Lin, Z., Duan, D., Yang, Q., Cheng, X., Yang, L., & Cui, S. (2019). Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources. In iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings (pp. 1021-1026). [8974949] (iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/iSPEC48194.2019.8974949

Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources. / Lin, Zhidi; Duan, Dongliang; Yang, Qi; Cheng, Xiang; Yang, Liuqing; Cui, Shuguang.

iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1021-1026 8974949 (iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings).

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

Lin, Z, Duan, D, Yang, Q, Cheng, X, Yang, L & Cui, S 2019, Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources. in iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings., 8974949, iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1021-1026, 2019 IEEE Sustainable Power and Energy Conference, iSPEC 2019, Beijing, China, 11/21/19. https://doi.org/10.1109/iSPEC48194.2019.8974949

Lin Z, Duan D, Yang Q, Cheng X, Yang L, Cui S. Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources. In iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1021-1026. 8974949. (iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings). https://doi.org/10.1109/iSPEC48194.2019.8974949

Lin, Zhidi ; Duan, Dongliang ; Yang, Qi ; Cheng, Xiang ; Yang, Liuqing ; Cui, Shuguang. / Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources. iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1021-1026 (iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings).

@inproceedings{f3b639daee144eeab1ebb8bcd6f1451c,

title = "Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources",

abstract = "The integration of Distributed Energy Resources (DERs) introduces non-conventional two-way power flows which cannot be captured well by traditional model-based techniques. This brings great challenges to accurately localize faults and initiate correct actions of the protection system. In this paper, we propose a data-driven fault localization strategy based on multilevel system regionalization and probabilistic fault detections on all the subregions. The strategy combines the Support Vector Data Description (SVDD) and the Kernel Density Estimation (KDE) to provide the confidence level of fault detections in each subregion by p-values, and then accurately localize the fault by comparing the p-values. Our experiments show that the proposed data-driven fault localization can greatly increase the accuracy of fault localization for distribution systems with high integration of DERs.",

keywords = "Distributed Energy Resources (DERs), Support Vector Data Description (SVDD), distribution systems, fault localization, probabilistic fault detection",

author = "Zhidi Lin and Dongliang Duan and Qi Yang and Xiang Cheng and Liuqing Yang and Shuguang Cui",

note = "Funding Information: ACKNOWLEDGMENT This work was supported in part by Shenzhen Fundamental Research Fund under Grant No. JCYJ20170411102217994 and ZDSYS201707251409055, Shenzhen Peacock Plan under Grant KQTD2015033114415450 and Guangdong province “The Pearl River Talent Recruitment Program Innovative and Entrepreneurial Teams in 2017” – Data Driven Evolution of Future Intelligent Network Team under grant No. 2017ZT07X152.; 2019 IEEE Sustainable Power and Energy Conference, iSPEC 2019 ; Conference date: 21-11-2019 Through 23-11-2019",

year = "2019",

month = nov,

doi = "10.1109/iSPEC48194.2019.8974949",

language = "English (US)",

series = "iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings",

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

pages = "1021--1026",

booktitle = "iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference",

}

TY - GEN

T1 - Data-Driven Fault Localization in Distribution Systems with Distributed Energy Resources

AU - Lin, Zhidi

AU - Duan, Dongliang

AU - Yang, Qi

AU - Cheng, Xiang

AU - Yang, Liuqing

AU - Cui, Shuguang

N1 - Funding Information: ACKNOWLEDGMENT This work was supported in part by Shenzhen Fundamental Research Fund under Grant No. JCYJ20170411102217994 and ZDSYS201707251409055, Shenzhen Peacock Plan under Grant KQTD2015033114415450 and Guangdong province “The Pearl River Talent Recruitment Program Innovative and Entrepreneurial Teams in 2017” – Data Driven Evolution of Future Intelligent Network Team under grant No. 2017ZT07X152.

PY - 2019/11

Y1 - 2019/11

N2 - The integration of Distributed Energy Resources (DERs) introduces non-conventional two-way power flows which cannot be captured well by traditional model-based techniques. This brings great challenges to accurately localize faults and initiate correct actions of the protection system. In this paper, we propose a data-driven fault localization strategy based on multilevel system regionalization and probabilistic fault detections on all the subregions. The strategy combines the Support Vector Data Description (SVDD) and the Kernel Density Estimation (KDE) to provide the confidence level of fault detections in each subregion by p-values, and then accurately localize the fault by comparing the p-values. Our experiments show that the proposed data-driven fault localization can greatly increase the accuracy of fault localization for distribution systems with high integration of DERs.

AB - The integration of Distributed Energy Resources (DERs) introduces non-conventional two-way power flows which cannot be captured well by traditional model-based techniques. This brings great challenges to accurately localize faults and initiate correct actions of the protection system. In this paper, we propose a data-driven fault localization strategy based on multilevel system regionalization and probabilistic fault detections on all the subregions. The strategy combines the Support Vector Data Description (SVDD) and the Kernel Density Estimation (KDE) to provide the confidence level of fault detections in each subregion by p-values, and then accurately localize the fault by comparing the p-values. Our experiments show that the proposed data-driven fault localization can greatly increase the accuracy of fault localization for distribution systems with high integration of DERs.

KW - Distributed Energy Resources (DERs)

KW - Support Vector Data Description (SVDD)

KW - distribution systems

KW - fault localization

KW - probabilistic fault detection

UR - http://www.scopus.com/inward/record.url?scp=85079505019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85079505019&partnerID=8YFLogxK

U2 - 10.1109/iSPEC48194.2019.8974949

DO - 10.1109/iSPEC48194.2019.8974949

M3 - Conference contribution

AN - SCOPUS:85079505019

T3 - iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference: Grid Modernization for Energy Revolution, Proceedings

SP - 1021

EP - 1026

BT - iSPEC 2019 - 2019 IEEE Sustainable Power and Energy Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE Sustainable Power and Energy Conference, iSPEC 2019

Y2 - 21 November 2019 through 23 November 2019

ER -