Classification of power system stability using support vector machines

Christian Andersson; J E Solem; B Eliasson

doi:10.1109/PES.2005.1489266

Classification of power system stability using support vector machines

Christian Andersson, J E Solem, B Eliasson

Division for Industrial Electrical Engineering and Automation

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

The last years' blackouts have indicated that even when a lot of data is available, the operators at different centers do not take the proper actions in time. This depends partly on the reorganization of the centers after the deregulation and partly on the lack of reliable supportive applications when the system is close to instability. This paper uses a novel technique based on support vector machines, SVM, in order to classify, if the power system can withstand a (n-1)-fault during a variety of operational conditions. The support vectors can be used on-line in order to determine if the system is moving into dangerous conditions and support the operators on an early stage, so proper actions can be made. This paper also shows that the scaling of the variables is important for good results. A new technique for finding the most important variables to measure or supervise is also presented.

Original language	English
Title of host publication	IEEE Power Engineering Society General Meeting, 2005
Publisher	IEEE - Institute of Electrical and Electronics Engineers Inc.
Pages	650-655
Volume	1
DOIs	https://doi.org/10.1109/PES.2005.1489266
Publication status	Published - 2005
Event	IEEE Power Engineering Society General Meeting, 2005 - San Francisco, California, United States Duration: 2005 Jun 12 → 2005 Jun 16

Publication series

Name
Volume	1

Conference

Conference	IEEE Power Engineering Society General Meeting, 2005
Country/Territory	United States
City	San Francisco, California
Period	2005/06/12 → 2005/06/16

Subject classification (UKÄ)

Other Electrical Engineering, Electronic Engineering, Information Engineering

Access to Document

10.1109/PES.2005.1489266

Cite this

@inproceedings{769a7b63edd74980975187be65d78a5b,

title = "Classification of power system stability using support vector machines",

abstract = "The last years' blackouts have indicated that even when a lot of data is available, the operators at different centers do not take the proper actions in time. This depends partly on the reorganization of the centers after the deregulation and partly on the lack of reliable supportive applications when the system is close to instability. This paper uses a novel technique based on support vector machines, SVM, in order to classify, if the power system can withstand a (n-1)-fault during a variety of operational conditions. The support vectors can be used on-line in order to determine if the system is moving into dangerous conditions and support the operators on an early stage, so proper actions can be made. This paper also shows that the scaling of the variables is important for good results. A new technique for finding the most important variables to measure or supervise is also presented.",

author = "Christian Andersson and Solem, \{J E\} and B Eliasson",

year = "2005",

doi = "10.1109/PES.2005.1489266",

language = "English",

volume = "1",

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

pages = "650--655",

booktitle = "IEEE Power Engineering Society General Meeting, 2005",

address = "United States",

note = "IEEE Power Engineering Society General Meeting, 2005 ; Conference date: 12-06-2005 Through 16-06-2005",

}

Andersson, C, Solem, JE & Eliasson, B 2005, Classification of power system stability using support vector machines. in IEEE Power Engineering Society General Meeting, 2005. vol. 1, IEEE - Institute of Electrical and Electronics Engineers Inc., pp. 650-655, IEEE Power Engineering Society General Meeting, 2005, San Francisco, California, United States, 2005/06/12. https://doi.org/10.1109/PES.2005.1489266

Classification of power system stability using support vector machines. / Andersson, Christian; Solem, J E; Eliasson, B.
IEEE Power Engineering Society General Meeting, 2005. Vol. 1 IEEE - Institute of Electrical and Electronics Engineers Inc., 2005. p. 650-655.

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Classification of power system stability using support vector machines

AU - Andersson, Christian

AU - Solem, J E

AU - Eliasson, B

PY - 2005

Y1 - 2005

N2 - The last years' blackouts have indicated that even when a lot of data is available, the operators at different centers do not take the proper actions in time. This depends partly on the reorganization of the centers after the deregulation and partly on the lack of reliable supportive applications when the system is close to instability. This paper uses a novel technique based on support vector machines, SVM, in order to classify, if the power system can withstand a (n-1)-fault during a variety of operational conditions. The support vectors can be used on-line in order to determine if the system is moving into dangerous conditions and support the operators on an early stage, so proper actions can be made. This paper also shows that the scaling of the variables is important for good results. A new technique for finding the most important variables to measure or supervise is also presented.

AB - The last years' blackouts have indicated that even when a lot of data is available, the operators at different centers do not take the proper actions in time. This depends partly on the reorganization of the centers after the deregulation and partly on the lack of reliable supportive applications when the system is close to instability. This paper uses a novel technique based on support vector machines, SVM, in order to classify, if the power system can withstand a (n-1)-fault during a variety of operational conditions. The support vectors can be used on-line in order to determine if the system is moving into dangerous conditions and support the operators on an early stage, so proper actions can be made. This paper also shows that the scaling of the variables is important for good results. A new technique for finding the most important variables to measure or supervise is also presented.

UR - https://www.scopus.com/pages/publications/27144545544

U2 - 10.1109/PES.2005.1489266

DO - 10.1109/PES.2005.1489266

M3 - Paper in conference proceeding

VL - 1

SP - 650

EP - 655

BT - IEEE Power Engineering Society General Meeting, 2005

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE Power Engineering Society General Meeting, 2005

Y2 - 12 June 2005 through 16 June 2005

ER -

Classification of power system stability using support vector machines

Abstract

Publication series

Conference

Subject classification (UKÄ)

Access to Document

Other files and links

Fingerprint

Cite this