Advanced

Classification of power system stability using support vector machines

Andersson, Christian LU ; Solem, J E and Eliasson, B (2005) IEEE Power Engineering Society General Meeting, 2005 In IEEE Power Engineering Society General Meeting, 2005 1. p.650-655
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
IEEE Power Engineering Society General Meeting, 2005
volume
1
pages
650 - 655
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE Power Engineering Society General Meeting, 2005
external identifiers
  • Scopus:27144545544
DOI
10.1109/PES.2005.1489266
language
English
LU publication?
yes
id
769a7b63-edd7-4980-9751-87be65d78a5b (old id 640889)
date added to LUP
2007-12-01 13:27:43
date last changed
2017-01-01 07:55:37
@inproceedings{769a7b63-edd7-4980-9751-87be65d78a5b,
  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       = {Andersson, Christian and Solem, J E and Eliasson, B},
  booktitle    = {IEEE Power Engineering Society General Meeting, 2005},
  language     = {eng},
  pages        = {650--655},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {Classification of power system stability using support vector machines},
  url          = {http://dx.doi.org/10.1109/PES.2005.1489266},
  volume       = {1},
  year         = {2005},
}