Active Power Oscillation Property Classification of Electric Power Systems Based on SVM
Nowadays, low frequency oscillation has become a major problem threatening the security of large-scale interconnected power systems. According to generation mechanism, active power oscillation of electric power systems can be classified into two categories: free oscillation and forced oscillation. T...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | Journal of Applied Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2014/218647 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850161925505155072 |
|---|---|
| author | Ju Liu Wei Yao Jinyu Wen Haibo He Xueyang Zheng |
| author_facet | Ju Liu Wei Yao Jinyu Wen Haibo He Xueyang Zheng |
| author_sort | Ju Liu |
| collection | DOAJ |
| description | Nowadays, low frequency oscillation has become a major problem threatening the security of large-scale interconnected power systems. According to generation mechanism, active power oscillation of electric power systems can be classified into two categories: free oscillation and forced oscillation. The former results from poor or negative damping ratio of power system and external periodic disturbance may lead to the latter. Thus control strategies to suppress the oscillations are totally different. Distinction from each other of those two different kinds of power oscillations becomes a precondition for suppressing the oscillations with proper measures. This paper proposes a practical approach for power oscillation classification by identifying real-time power oscillation curves. Hilbert transform is employed to obtain envelope curves of the power oscillation curves. Twenty sampling points of the envelope curve are selected as the feature matrices to train and test the supporting vector machine (SVM). The tests on the 16-machine 68-bus benchmark power system and a real power system in China indicate that the proposed oscillation classification method is of high precision. |
| format | Article |
| id | doaj-art-fd6dbf9cce9f484794ddddfb387b8879 |
| institution | OA Journals |
| issn | 1110-757X 1687-0042 |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Applied Mathematics |
| spelling | doaj-art-fd6dbf9cce9f484794ddddfb387b88792025-08-20T02:22:40ZengWileyJournal of Applied Mathematics1110-757X1687-00422014-01-01201410.1155/2014/218647218647Active Power Oscillation Property Classification of Electric Power Systems Based on SVMJu Liu0Wei Yao1Jinyu Wen2Haibo He3Xueyang Zheng4The State Key Laboratory of Advanced Electromagnetic Engineering and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaThe State Key Laboratory of Advanced Electromagnetic Engineering and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaThe State Key Laboratory of Advanced Electromagnetic Engineering and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaDepartment of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Kingston, RI 02881, USAThe State Key Laboratory of Advanced Electromagnetic Engineering and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaNowadays, low frequency oscillation has become a major problem threatening the security of large-scale interconnected power systems. According to generation mechanism, active power oscillation of electric power systems can be classified into two categories: free oscillation and forced oscillation. The former results from poor or negative damping ratio of power system and external periodic disturbance may lead to the latter. Thus control strategies to suppress the oscillations are totally different. Distinction from each other of those two different kinds of power oscillations becomes a precondition for suppressing the oscillations with proper measures. This paper proposes a practical approach for power oscillation classification by identifying real-time power oscillation curves. Hilbert transform is employed to obtain envelope curves of the power oscillation curves. Twenty sampling points of the envelope curve are selected as the feature matrices to train and test the supporting vector machine (SVM). The tests on the 16-machine 68-bus benchmark power system and a real power system in China indicate that the proposed oscillation classification method is of high precision.http://dx.doi.org/10.1155/2014/218647 |
| spellingShingle | Ju Liu Wei Yao Jinyu Wen Haibo He Xueyang Zheng Active Power Oscillation Property Classification of Electric Power Systems Based on SVM Journal of Applied Mathematics |
| title | Active Power Oscillation Property Classification of Electric Power Systems Based on SVM |
| title_full | Active Power Oscillation Property Classification of Electric Power Systems Based on SVM |
| title_fullStr | Active Power Oscillation Property Classification of Electric Power Systems Based on SVM |
| title_full_unstemmed | Active Power Oscillation Property Classification of Electric Power Systems Based on SVM |
| title_short | Active Power Oscillation Property Classification of Electric Power Systems Based on SVM |
| title_sort | active power oscillation property classification of electric power systems based on svm |
| url | http://dx.doi.org/10.1155/2014/218647 |
| work_keys_str_mv | AT juliu activepoweroscillationpropertyclassificationofelectricpowersystemsbasedonsvm AT weiyao activepoweroscillationpropertyclassificationofelectricpowersystemsbasedonsvm AT jinyuwen activepoweroscillationpropertyclassificationofelectricpowersystemsbasedonsvm AT haibohe activepoweroscillationpropertyclassificationofelectricpowersystemsbasedonsvm AT xueyangzheng activepoweroscillationpropertyclassificationofelectricpowersystemsbasedonsvm |