Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble Learning
Transient stability assessment (TSA) is of great importance in power system operation and control. One of the usual tasks in TSA is to estimate the critical clearing time (CCT) of a given fault under the given network topology and pre-fault power flow. Data-driven methods try to obtain models descri...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | Journal of Modern Power Systems and Clean Energy |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9275596/ |
id |
doaj-c0c0b5493dab41868efb4a382214e6c2 |
---|---|
record_format |
Article |
spelling |
doaj-c0c0b5493dab41868efb4a382214e6c22021-04-23T16:15:34ZengIEEEJournal of Modern Power Systems and Clean Energy2196-54202020-01-01861080109110.35833/MPCE.2020.0003419275596Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble LearningXianzhuang Liu0Xiaohua Zhang1Lei Chen2Fei Xu3Changyou Feng4State Grid Corporation of China,Beijing,China,100031State Grid Jibei Electric Power Company,Beijing,China,100053State Key Laboratory of Control and Simulation of Power System and Generation Equipment, Tsinghua University,Department of Electrical Engineering,Beijing,China,100084State Key Laboratory of Control and Simulation of Power System and Generation Equipment, Tsinghua University,Department of Electrical Engineering,Beijing,China,100084State Grid Corporation of China,Beijing,China,100031Transient stability assessment (TSA) is of great importance in power system operation and control. One of the usual tasks in TSA is to estimate the critical clearing time (CCT) of a given fault under the given network topology and pre-fault power flow. Data-driven methods try to obtain models describing the mapping between these factors and the CCT from a large number of samples. However, the influence of network topology on CCT is hard to be analyzed and is often ignored, which makes the models inaccurate and unpractical. In this paper, a novel data-driven TSA model combining Mahalanobis kernel regression and ensemble learning is proposed to deal with the problem. The model is a weighted sum of several sub-models. Each sub-model only uses the data of one topology to construct a kernel regressor. The weights are determined by both the topological similarity and numerical similarity between the samples. The similarities are decided by the parameters in Mahalanobis distance, and the parameters are to be trained. To reduce the model complexity, sub-models within the same topology category share the same parameters. When estimating CCT, the model uses not only the sub-model which the sample topology belongs to, but also other sub-models. Thus, it avoids the problem that there may be too few data under some topologies. It also efficiently utilizes information of data under all the topologies. Moreover, its decision-making process is clear and understandable, and an effective training algorithm is also designed. Test results on both the IEEE 10-machine 39-bus and a real system verify the effectiveness of the proposed model.https://ieeexplore.ieee.org/document/9275596/Transient stability assessmentcritical clearing timenetwork topology changeMahalanobis kernel regressionensemble learningdata-driven |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xianzhuang Liu Xiaohua Zhang Lei Chen Fei Xu Changyou Feng |
spellingShingle |
Xianzhuang Liu Xiaohua Zhang Lei Chen Fei Xu Changyou Feng Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble Learning Journal of Modern Power Systems and Clean Energy Transient stability assessment critical clearing time network topology change Mahalanobis kernel regression ensemble learning data-driven |
author_facet |
Xianzhuang Liu Xiaohua Zhang Lei Chen Fei Xu Changyou Feng |
author_sort |
Xianzhuang Liu |
title |
Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble Learning |
title_short |
Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble Learning |
title_full |
Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble Learning |
title_fullStr |
Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble Learning |
title_full_unstemmed |
Data-driven Transient Stability Assessment Model Considering Network Topology Changes via Mahalanobis Kernel Regression and Ensemble Learning |
title_sort |
data-driven transient stability assessment model considering network topology changes via mahalanobis kernel regression and ensemble learning |
publisher |
IEEE |
series |
Journal of Modern Power Systems and Clean Energy |
issn |
2196-5420 |
publishDate |
2020-01-01 |
description |
Transient stability assessment (TSA) is of great importance in power system operation and control. One of the usual tasks in TSA is to estimate the critical clearing time (CCT) of a given fault under the given network topology and pre-fault power flow. Data-driven methods try to obtain models describing the mapping between these factors and the CCT from a large number of samples. However, the influence of network topology on CCT is hard to be analyzed and is often ignored, which makes the models inaccurate and unpractical. In this paper, a novel data-driven TSA model combining Mahalanobis kernel regression and ensemble learning is proposed to deal with the problem. The model is a weighted sum of several sub-models. Each sub-model only uses the data of one topology to construct a kernel regressor. The weights are determined by both the topological similarity and numerical similarity between the samples. The similarities are decided by the parameters in Mahalanobis distance, and the parameters are to be trained. To reduce the model complexity, sub-models within the same topology category share the same parameters. When estimating CCT, the model uses not only the sub-model which the sample topology belongs to, but also other sub-models. Thus, it avoids the problem that there may be too few data under some topologies. It also efficiently utilizes information of data under all the topologies. Moreover, its decision-making process is clear and understandable, and an effective training algorithm is also designed. Test results on both the IEEE 10-machine 39-bus and a real system verify the effectiveness of the proposed model. |
topic |
Transient stability assessment critical clearing time network topology change Mahalanobis kernel regression ensemble learning data-driven |
url |
https://ieeexplore.ieee.org/document/9275596/ |
work_keys_str_mv |
AT xianzhuangliu datadriventransientstabilityassessmentmodelconsideringnetworktopologychangesviamahalanobiskernelregressionandensemblelearning AT xiaohuazhang datadriventransientstabilityassessmentmodelconsideringnetworktopologychangesviamahalanobiskernelregressionandensemblelearning AT leichen datadriventransientstabilityassessmentmodelconsideringnetworktopologychangesviamahalanobiskernelregressionandensemblelearning AT feixu datadriventransientstabilityassessmentmodelconsideringnetworktopologychangesviamahalanobiskernelregressionandensemblelearning AT changyoufeng datadriventransientstabilityassessmentmodelconsideringnetworktopologychangesviamahalanobiskernelregressionandensemblelearning |
_version_ |
1721512458980425728 |