Spectral MST-Based Graph Outlier Detection With Application to Clustering of Power Networks

Ilya Tyuryukanov; Marjan Popov; Mart A.M.M. Van Der Meijden; Vladimir Terzija

doi:10.23919/PSCC.2018.8442671

Spectral MST-Based Graph Outlier Detection With Application to Clustering of Power Networks

Ilya Tyuryukanov, Marjan Popov, Mart A.M.M. Van Der Meijden, Vladimir Terzija

Intelligent Electrical Power Grids

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

1 Citation (Scopus)

18 Downloads (Pure)

Abstract

An increasing number of methods for control and analysis of power systems relies on representing power networks as weighted undirected graphs. Unfortunately, the presence of outliers in power system graphs may have a negative impact on many of these methods. In addition, detecting outliers can be a relevant task on its own. Motivated by the low number of outlier detection algorithms focusing on weighted undirected graphs, this paper proposes an efficient and effective method to detect loosely connected graph clusters below a certain number of nodes. The essence of the method lies in the efficient examination of the spectral minimal spanning tree of the input graph. The obtained results on several large test power networks validate the high outlier detection performance of the proposed method and its high computational efficiency.

Original language	English
Title of host publication	20th Power Systems Computation Conference (PSCC)
Publisher	IEEE
Pages	1-8
Number of pages	8
ISBN (Electronic)	978-1-910963-10-4
ISBN (Print)	978-1-5386-1583-6
DOIs	https://doi.org/10.23919/PSCC.2018.8442671
Publication status	Published - 2018
Event	20th Power Systems Computation Conference, PSCC 2018 - Dublin, Ireland Duration: 11 Jun 2018 → 15 Jun 2018 http://www.pscc2018.net/

Conference

Conference	20th Power Systems Computation Conference, PSCC 2018
Country/Territory	Ireland
City	Dublin
Period	11/06/18 → 15/06/18
Internet address	http://www.pscc2018.net/

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Graph outlier detection
Outliers
Power network partitioning
Power system analysis computing

Access to Document

10.23919/PSCC.2018.8442671

08442671Final published version, 470 KB

Cite this

@inproceedings{82afae5a151d4a3b9a53b533f70b9ef1,

title = "Spectral MST-Based Graph Outlier Detection With Application to Clustering of Power Networks",

abstract = "An increasing number of methods for control and analysis of power systems relies on representing power networks as weighted undirected graphs. Unfortunately, the presence of outliers in power system graphs may have a negative impact on many of these methods. In addition, detecting outliers can be a relevant task on its own. Motivated by the low number of outlier detection algorithms focusing on weighted undirected graphs, this paper proposes an efficient and effective method to detect loosely connected graph clusters below a certain number of nodes. The essence of the method lies in the efficient examination of the spectral minimal spanning tree of the input graph. The obtained results on several large test power networks validate the high outlier detection performance of the proposed method and its high computational efficiency.",

keywords = "Graph outlier detection, Outliers, Power network partitioning, Power system analysis computing",

author = "Ilya Tyuryukanov and Marjan Popov and {Van Der Meijden}, {Mart A.M.M.} and Vladimir Terzija",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 20th Power Systems Computation Conference, PSCC 2018 ; Conference date: 11-06-2018 Through 15-06-2018",

year = "2018",

doi = "10.23919/PSCC.2018.8442671",

language = "English",

isbn = "978-1-5386-1583-6 ",

pages = "1--8",

booktitle = "20th Power Systems Computation Conference (PSCC)",

publisher = "IEEE",

address = "United States",

url = "http://www.pscc2018.net/",

}

Spectral MST-Based Graph Outlier Detection With Application to Clustering of Power Networks. / Tyuryukanov, Ilya; Popov, Marjan ; Van Der Meijden, Mart A.M.M. et al.
20th Power Systems Computation Conference (PSCC). IEEE, 2018. p. 1-8 8442671.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Spectral MST-Based Graph Outlier Detection With Application to Clustering of Power Networks

AU - Tyuryukanov, Ilya

AU - Popov, Marjan

AU - Van Der Meijden, Mart A.M.M.

AU - Terzija, Vladimir

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2018

Y1 - 2018

N2 - An increasing number of methods for control and analysis of power systems relies on representing power networks as weighted undirected graphs. Unfortunately, the presence of outliers in power system graphs may have a negative impact on many of these methods. In addition, detecting outliers can be a relevant task on its own. Motivated by the low number of outlier detection algorithms focusing on weighted undirected graphs, this paper proposes an efficient and effective method to detect loosely connected graph clusters below a certain number of nodes. The essence of the method lies in the efficient examination of the spectral minimal spanning tree of the input graph. The obtained results on several large test power networks validate the high outlier detection performance of the proposed method and its high computational efficiency.

AB - An increasing number of methods for control and analysis of power systems relies on representing power networks as weighted undirected graphs. Unfortunately, the presence of outliers in power system graphs may have a negative impact on many of these methods. In addition, detecting outliers can be a relevant task on its own. Motivated by the low number of outlier detection algorithms focusing on weighted undirected graphs, this paper proposes an efficient and effective method to detect loosely connected graph clusters below a certain number of nodes. The essence of the method lies in the efficient examination of the spectral minimal spanning tree of the input graph. The obtained results on several large test power networks validate the high outlier detection performance of the proposed method and its high computational efficiency.

KW - Graph outlier detection

KW - Outliers

KW - Power network partitioning

KW - Power system analysis computing

UR - http://www.scopus.com/inward/record.url?scp=85054006227&partnerID=8YFLogxK

U2 - 10.23919/PSCC.2018.8442671

DO - 10.23919/PSCC.2018.8442671

M3 - Conference contribution

AN - SCOPUS:85054006227

SN - 978-1-5386-1583-6

SP - 1

EP - 8

BT - 20th Power Systems Computation Conference (PSCC)

PB - IEEE

T2 - 20th Power Systems Computation Conference, PSCC 2018

Y2 - 11 June 2018 through 15 June 2018

ER -

Spectral MST-Based Graph Outlier Detection With Application to Clustering of Power Networks

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this