LEARNING to INFER POWER GRID TOPOLOGIES: PERFORMANCE and SCALABILITY

Yue Zhao; Jianshu Chen; H. Vincent Poor

doi:10.1109/DSW.2018.8439902

LEARNING to INFER POWER GRID TOPOLOGIES: PERFORMANCE and SCALABILITY

Yue Zhao, Jianshu Chen, H. Vincent Poor

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

2 Scopus citations

Abstract

Identifying arbitrary topologies of power networks in real time is a computationally hard problem due to the number of hypotheses that grows exponentially with the network size. A 'Learning-to-Infer' variational inference method is employed for efficient inference of every line status in the network. Optimizing the variational model is transformed to and solved as a discriminative learning problem based on Monte Carlo samples generated with power flow simulations. As the labeled data used for training can be generated in an arbitrarily large amount rapidly and at very little cost, the power of offline training is fully exploited to learn very complex classifiers for effective real-time topology identification. The Learning-to-Infer method is extensively evaluated in the IEEE 30, 118 and 300 bus systems. Excellent performance and scalability of the method in identifying arbitrary power network topologies in real time are demonstrated.

Original language	English (US)
Title of host publication	2018 IEEE Data Science Workshop, DSW 2018 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	215-219
Number of pages	5
ISBN (Print)	9781538644102
DOIs	https://doi.org/10.1109/DSW.2018.8439902
State	Published - Aug 17 2018
Event	2018 IEEE Data Science Workshop, DSW 2018 - Lausanne, Switzerland Duration: Jun 4 2018 → Jun 6 2018

Publication series

Name	2018 IEEE Data Science Workshop, DSW 2018 - Proceedings

Other

Other	2018 IEEE Data Science Workshop, DSW 2018
Country/Territory	Switzerland
City	Lausanne
Period	6/4/18 → 6/6/18

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Safety, Risk, Reliability and Quality
Water Science and Technology
Control and Optimization

Keywords

cascading failures
line outage detection
machine learning
power grid topology identification

Access to Document

10.1109/DSW.2018.8439902

Cite this

@inproceedings{c6510947e718475988f257cc5c4231f8,

title = "LEARNING to INFER POWER GRID TOPOLOGIES: PERFORMANCE and SCALABILITY",

abstract = "Identifying arbitrary topologies of power networks in real time is a computationally hard problem due to the number of hypotheses that grows exponentially with the network size. A 'Learning-to-Infer' variational inference method is employed for efficient inference of every line status in the network. Optimizing the variational model is transformed to and solved as a discriminative learning problem based on Monte Carlo samples generated with power flow simulations. As the labeled data used for training can be generated in an arbitrarily large amount rapidly and at very little cost, the power of offline training is fully exploited to learn very complex classifiers for effective real-time topology identification. The Learning-to-Infer method is extensively evaluated in the IEEE 30, 118 and 300 bus systems. Excellent performance and scalability of the method in identifying arbitrary power network topologies in real time are demonstrated.",

keywords = "cascading failures, line outage detection, machine learning, power grid topology identification",

author = "Yue Zhao and Jianshu Chen and Poor, {H. Vincent}",

note = "Funding Information: This work was supported in part by the U.S. National Science Foundation under Grant DMS-1736417. Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE Data Science Workshop, DSW 2018 ; Conference date: 04-06-2018 Through 06-06-2018",

year = "2018",

month = aug,

day = "17",

doi = "10.1109/DSW.2018.8439902",

language = "English (US)",

isbn = "9781538644102",

series = "2018 IEEE Data Science Workshop, DSW 2018 - Proceedings",

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

pages = "215--219",

booktitle = "2018 IEEE Data Science Workshop, DSW 2018 - Proceedings",

address = "United States",

}

Zhao, Y, Chen, J & Poor, HV 2018, LEARNING to INFER POWER GRID TOPOLOGIES: PERFORMANCE and SCALABILITY. in 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings., 8439902, 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 215-219, 2018 IEEE Data Science Workshop, DSW 2018, Lausanne, Switzerland, 6/4/18. https://doi.org/10.1109/DSW.2018.8439902

LEARNING to INFER POWER GRID TOPOLOGIES: PERFORMANCE and SCALABILITY. / Zhao, Yue; Chen, Jianshu; Poor, H. Vincent.
2018 IEEE Data Science Workshop, DSW 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 215-219 8439902 (2018 IEEE Data Science Workshop, DSW 2018 - Proceedings).

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

TY - GEN

T1 - LEARNING to INFER POWER GRID TOPOLOGIES

T2 - 2018 IEEE Data Science Workshop, DSW 2018

AU - Zhao, Yue

AU - Chen, Jianshu

AU - Poor, H. Vincent

PY - 2018/8/17

Y1 - 2018/8/17

N2 - Identifying arbitrary topologies of power networks in real time is a computationally hard problem due to the number of hypotheses that grows exponentially with the network size. A 'Learning-to-Infer' variational inference method is employed for efficient inference of every line status in the network. Optimizing the variational model is transformed to and solved as a discriminative learning problem based on Monte Carlo samples generated with power flow simulations. As the labeled data used for training can be generated in an arbitrarily large amount rapidly and at very little cost, the power of offline training is fully exploited to learn very complex classifiers for effective real-time topology identification. The Learning-to-Infer method is extensively evaluated in the IEEE 30, 118 and 300 bus systems. Excellent performance and scalability of the method in identifying arbitrary power network topologies in real time are demonstrated.

AB - Identifying arbitrary topologies of power networks in real time is a computationally hard problem due to the number of hypotheses that grows exponentially with the network size. A 'Learning-to-Infer' variational inference method is employed for efficient inference of every line status in the network. Optimizing the variational model is transformed to and solved as a discriminative learning problem based on Monte Carlo samples generated with power flow simulations. As the labeled data used for training can be generated in an arbitrarily large amount rapidly and at very little cost, the power of offline training is fully exploited to learn very complex classifiers for effective real-time topology identification. The Learning-to-Infer method is extensively evaluated in the IEEE 30, 118 and 300 bus systems. Excellent performance and scalability of the method in identifying arbitrary power network topologies in real time are demonstrated.

KW - cascading failures

KW - line outage detection

KW - machine learning

KW - power grid topology identification

UR - http://www.scopus.com/inward/record.url?scp=85053153705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053153705&partnerID=8YFLogxK

U2 - 10.1109/DSW.2018.8439902

DO - 10.1109/DSW.2018.8439902

M3 - Conference contribution

AN - SCOPUS:85053153705

SN - 9781538644102

T3 - 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings

SP - 215

EP - 219

BT - 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 4 June 2018 through 6 June 2018

ER -

LEARNING to INFER POWER GRID TOPOLOGIES: PERFORMANCE and SCALABILITY

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this