Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees

Chengxi Liu; Claus Leth Bak; Zhe Chen; Per  Lund

doi:10.1049/cp.2014.0150

Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees

Chengxi Liu, Claus Leth Bak, Zhe Chen, Per Lund

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

1 Citation (Scopus)

650 Downloads (Pure)

Abstract

With the increasing penetration of renewable energy resources and other forms of dispersed generation, more and more uncertainties will be brought to the dynamic security assessment (DSA) of power systems. This paper proposes an approach that uses ensemble decision trees (EDT) for online DSA. Fed with online wide-area measurement data, it is capable of not only predicting the security states of current operating conditions (OC) with high accuracy, but also indicating the confidence of the security states 1 minute ahead of the real time by an outlier identification method. The results of EDT together with outlier identification show high accuracy in the presence of variance and uncertainties due to wind power generation and other dispersed generation units.
The performance of this approach is demonstrated on the operational model of western Danish power system with the scale of around 200 lines and 400 buses.

Original language	English
Title of host publication	Proceedings of the 12th International Conference on Developments in Power System Protection, DPSP 2014
Number of pages	6
Publisher	Institution of Engineering and Technology
Publication date	Mar 2014
Pages	1-6
ISBN (Print)	978-1-84919-834-9
DOIs	https://doi.org/10.1049/cp.2014.0150
Publication status	Published - Mar 2014
Event	12th International Conference on Developments in Power System Protection, DPSP 2014 - Copenhagen, Denmark Duration: 31 Mar 2014 → 3 Apr 2014

Conference

Conference	12th International Conference on Developments in Power System Protection, DPSP 2014
Country/Territory	Denmark
City	Copenhagen
Period	31/03/2014 → 03/04/2014

Keywords

Dispersed generation
Dynamic security assessment
Ensemble decision trees
Wide-area measurement

Access to Document

10.1049/cp.2014.0150

Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision TreesAccepted author manuscript, 388 KB

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6822958&queryText%3DDynamic+Security+Assessment+of+Western+Danish+Power+System+Based+on+Ensemble+Decision+Trees

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{2f30e5841382469cb12e29140b3153fd,

title = "Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees",

abstract = "With the increasing penetration of renewable energy resources and other forms of dispersed generation, more and more uncertainties will be brought to the dynamic security assessment (DSA) of power systems. This paper proposes an approach that uses ensemble decision trees (EDT) for online DSA. Fed with online wide-area measurement data, it is capable of not only predicting the security states of current operating conditions (OC) with high accuracy, but also indicating the confidence of the security states 1 minute ahead of the real time by an outlier identification method. The results of EDT together with outlier identification show high accuracy in the presence of variance and uncertainties due to wind power generation and other dispersed generation units.The performance of this approach is demonstrated on the operational model of western Danish power system with the scale of around 200 lines and 400 buses.",

keywords = "Dispersed generation, Dynamic security assessment, Ensemble decision trees, Wide-area measurement",

author = "Chengxi Liu and Bak, {Claus Leth} and Zhe Chen and Per Lund",

year = "2014",

month = mar,

doi = "10.1049/cp.2014.0150",

language = "English",

isbn = "978-1-84919-834-9 ",

pages = "1--6",

booktitle = "Proceedings of the 12th International Conference on Developments in Power System Protection, DPSP 2014",

publisher = "Institution of Engineering and Technology",

address = "United States",

note = "12th International Conference on Developments in Power System Protection, DPSP 2014 ; Conference date: 31-03-2014 Through 03-04-2014",

}

Liu, C, Bak, CL , Chen, Z & Lund, P 2014, Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees. in Proceedings of the 12th International Conference on Developments in Power System Protection, DPSP 2014. Institution of Engineering and Technology, pp. 1-6, 12th International Conference on Developments in Power System Protection, DPSP 2014, Copenhagen, Denmark, 31/03/2014. https://doi.org/10.1049/cp.2014.0150

Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees. / Liu, Chengxi; Bak, Claus Leth ; Chen, Zhe et al.
Proceedings of the 12th International Conference on Developments in Power System Protection, DPSP 2014. Institution of Engineering and Technology, 2014. p. 1-6.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees

AU - Liu, Chengxi

AU - Bak, Claus Leth

AU - Chen, Zhe

AU - Lund, Per

PY - 2014/3

Y1 - 2014/3

N2 - With the increasing penetration of renewable energy resources and other forms of dispersed generation, more and more uncertainties will be brought to the dynamic security assessment (DSA) of power systems. This paper proposes an approach that uses ensemble decision trees (EDT) for online DSA. Fed with online wide-area measurement data, it is capable of not only predicting the security states of current operating conditions (OC) with high accuracy, but also indicating the confidence of the security states 1 minute ahead of the real time by an outlier identification method. The results of EDT together with outlier identification show high accuracy in the presence of variance and uncertainties due to wind power generation and other dispersed generation units.The performance of this approach is demonstrated on the operational model of western Danish power system with the scale of around 200 lines and 400 buses.

AB - With the increasing penetration of renewable energy resources and other forms of dispersed generation, more and more uncertainties will be brought to the dynamic security assessment (DSA) of power systems. This paper proposes an approach that uses ensemble decision trees (EDT) for online DSA. Fed with online wide-area measurement data, it is capable of not only predicting the security states of current operating conditions (OC) with high accuracy, but also indicating the confidence of the security states 1 minute ahead of the real time by an outlier identification method. The results of EDT together with outlier identification show high accuracy in the presence of variance and uncertainties due to wind power generation and other dispersed generation units.The performance of this approach is demonstrated on the operational model of western Danish power system with the scale of around 200 lines and 400 buses.

KW - Dispersed generation

KW - Dynamic security assessment

KW - Ensemble decision trees

KW - Wide-area measurement

UR - http://www.scopus.com/inward/record.url?scp=84902589405&partnerID=8YFLogxK

U2 - 10.1049/cp.2014.0150

DO - 10.1049/cp.2014.0150

M3 - Article in proceeding

SN - 978-1-84919-834-9

SP - 1

EP - 6

BT - Proceedings of the 12th International Conference on Developments in Power System Protection, DPSP 2014

PB - Institution of Engineering and Technology

T2 - 12th International Conference on Developments in Power System Protection, DPSP 2014

Y2 - 31 March 2014 through 3 April 2014

ER -

Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Development of a Secure, Economic and Environmentally-friendly Modern Power System

Cite this

Dynamic Security Assessment of Western Danish Power System Based on Ensemble Decision Trees

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Projects

Development of a Secure, Economic and Environmentally-friendly Modern Power System

Cite this