Online Recognition Method for Voltage Sags Based on a Deep Belief Network
Voltage sag is a serious power quality phenomenon that threatens industrial manufacturing and residential electricity. A large-scale monitoring system has been established and continually improved to detect and record voltage sag events. However, the inefficient process of data sampling cannot provi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/12/1/43 |
| _version_ | 1798039679089508352 |
|---|---|
| author | Fei Mei Yong Ren Qingliang Wu Chenyu Zhang Yi Pan Haoyuan Sha Jianyong Zheng |
| author_facet | Fei Mei Yong Ren Qingliang Wu Chenyu Zhang Yi Pan Haoyuan Sha Jianyong Zheng |
| author_sort | Fei Mei |
| collection | DOAJ |
| description | Voltage sag is a serious power quality phenomenon that threatens industrial manufacturing and residential electricity. A large-scale monitoring system has been established and continually improved to detect and record voltage sag events. However, the inefficient process of data sampling cannot provide valuable information early enough for governance of the system. Therefore, a novel online recognition method for voltage sags is proposed. The main contributions of this paper include: 1) The causes and waveform characters of voltage sags were analyzed; 2) according to the characters of different sag waveforms, 10 voltage sag characteristic parameters were proposed and proven to be effective; 3) a deep belief network (DBN) model was built using these parameters to complete automatic recognition of the sag event types. Experiments were conducted using voltage sag data from one month recorded by the 10 kV monitoring points in Suqian, Jiangsu Province, China. The results showed good performance of the proposed method: Recognition accuracy was 96.92%. The test results from the proposed method were compared to the results from support vector machine (SVM) recognition methods. The proposed method was shown to outperform SVM. |
| first_indexed | 2024-04-11T21:57:09Z |
| format | Article |
| id | doaj.art-e541e09cc0bc4fe0be4fa45b19e39c8a |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T21:57:09Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-e541e09cc0bc4fe0be4fa45b19e39c8a2022-12-22T04:01:04ZengMDPI AGEnergies1996-10732018-12-011214310.3390/en12010043en12010043Online Recognition Method for Voltage Sags Based on a Deep Belief NetworkFei Mei0Yong Ren1Qingliang Wu2Chenyu Zhang3Yi Pan4Haoyuan Sha5Jianyong Zheng6College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, ChinaCollege of Energy and Electrical Engineering, Hohai University, Nanjing 211100, ChinaCollege of Energy and Electrical Engineering, Hohai University, Nanjing 211100, ChinaState Grid Jiangsu Electric Power Co., Ltd. Research Institute, Nanjing 211113, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210096, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210096, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210096, ChinaVoltage sag is a serious power quality phenomenon that threatens industrial manufacturing and residential electricity. A large-scale monitoring system has been established and continually improved to detect and record voltage sag events. However, the inefficient process of data sampling cannot provide valuable information early enough for governance of the system. Therefore, a novel online recognition method for voltage sags is proposed. The main contributions of this paper include: 1) The causes and waveform characters of voltage sags were analyzed; 2) according to the characters of different sag waveforms, 10 voltage sag characteristic parameters were proposed and proven to be effective; 3) a deep belief network (DBN) model was built using these parameters to complete automatic recognition of the sag event types. Experiments were conducted using voltage sag data from one month recorded by the 10 kV monitoring points in Suqian, Jiangsu Province, China. The results showed good performance of the proposed method: Recognition accuracy was 96.92%. The test results from the proposed method were compared to the results from support vector machine (SVM) recognition methods. The proposed method was shown to outperform SVM.http://www.mdpi.com/1996-1073/12/1/43online recognitionvoltage sagdeep belief network |
| spellingShingle | Fei Mei Yong Ren Qingliang Wu Chenyu Zhang Yi Pan Haoyuan Sha Jianyong Zheng Online Recognition Method for Voltage Sags Based on a Deep Belief Network Energies online recognition voltage sag deep belief network |
| title | Online Recognition Method for Voltage Sags Based on a Deep Belief Network |
| title_full | Online Recognition Method for Voltage Sags Based on a Deep Belief Network |
| title_fullStr | Online Recognition Method for Voltage Sags Based on a Deep Belief Network |
| title_full_unstemmed | Online Recognition Method for Voltage Sags Based on a Deep Belief Network |
| title_short | Online Recognition Method for Voltage Sags Based on a Deep Belief Network |
| title_sort | online recognition method for voltage sags based on a deep belief network |
| topic | online recognition voltage sag deep belief network |
| url | http://www.mdpi.com/1996-1073/12/1/43 |
| work_keys_str_mv | AT feimei onlinerecognitionmethodforvoltagesagsbasedonadeepbeliefnetwork AT yongren onlinerecognitionmethodforvoltagesagsbasedonadeepbeliefnetwork AT qingliangwu onlinerecognitionmethodforvoltagesagsbasedonadeepbeliefnetwork AT chenyuzhang onlinerecognitionmethodforvoltagesagsbasedonadeepbeliefnetwork AT yipan onlinerecognitionmethodforvoltagesagsbasedonadeepbeliefnetwork AT haoyuansha onlinerecognitionmethodforvoltagesagsbasedonadeepbeliefnetwork AT jianyongzheng onlinerecognitionmethodforvoltagesagsbasedonadeepbeliefnetwork |