A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model
Abstract Out-of-step protection of one or a group of synchronous generators is unreliable in a power system which has significant renewable power penetration. In this work, an innovative out-of-step protection algorithm using wavelet transform and deep learning is presented to protect synchronous ge...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-12-01
|
| Series: | Protection and Control of Modern Power Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41601-021-00221-y |
| _version_ | 1818361174047064064 |
|---|---|
| author | Jigneshkumar Pramodbhai Desai Vijay Hiralal Makwana |
| author_facet | Jigneshkumar Pramodbhai Desai Vijay Hiralal Makwana |
| author_sort | Jigneshkumar Pramodbhai Desai |
| collection | DOAJ |
| description | Abstract Out-of-step protection of one or a group of synchronous generators is unreliable in a power system which has significant renewable power penetration. In this work, an innovative out-of-step protection algorithm using wavelet transform and deep learning is presented to protect synchronous generators and transmission lines. The specific patterns are generated from both stable and unstable power swing, and three-phase fault using the wavelet transform technique. Data containing 27,008 continuous samples of 48 different features is used to train a two-layer feed-forward network. The proposed algorithm gives an automatic, setting free and highly accurate classification for the three-phase fault, stable power swing, and unstable power swing through pattern recognition within a half cycle. The proposed algorithm uses the Kundur 2-area system and a 29-bus electric network for testing under different swing center locations and levels of renewable power penetration. Hardware-in-the-loop (HIL) tests show the hardware compatibility of the developed out-of-step algorithm. The proposed algorithm is also compared with recently reported algorithms. The comparison and test results on different large-scale systems show that the proposed algorithm is simple, fast, accurate, and HIL tested, and not affected by changes in power system parameters. |
| first_indexed | 2024-12-13T21:12:29Z |
| format | Article |
| id | doaj.art-c3175f01d00c43e5a581b88ea8205755 |
| institution | Directory Open Access Journal |
| issn | 2367-2617 2367-0983 |
| language | English |
| last_indexed | 2024-12-13T21:12:29Z |
| publishDate | 2021-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Protection and Control of Modern Power Systems |
| spelling | doaj.art-c3175f01d00c43e5a581b88ea82057552022-12-21T23:31:19ZengSpringerOpenProtection and Control of Modern Power Systems2367-26172367-09832021-12-016111210.1186/s41601-021-00221-yA novel out of step relaying algorithm based on wavelet transform and a deep learning machine modelJigneshkumar Pramodbhai Desai0Vijay Hiralal Makwana1Gujarat Technological UniversityElectrical Engineering Department, G.H. Patel College of Engineering and Technology, CVM UniversityAbstract Out-of-step protection of one or a group of synchronous generators is unreliable in a power system which has significant renewable power penetration. In this work, an innovative out-of-step protection algorithm using wavelet transform and deep learning is presented to protect synchronous generators and transmission lines. The specific patterns are generated from both stable and unstable power swing, and three-phase fault using the wavelet transform technique. Data containing 27,008 continuous samples of 48 different features is used to train a two-layer feed-forward network. The proposed algorithm gives an automatic, setting free and highly accurate classification for the three-phase fault, stable power swing, and unstable power swing through pattern recognition within a half cycle. The proposed algorithm uses the Kundur 2-area system and a 29-bus electric network for testing under different swing center locations and levels of renewable power penetration. Hardware-in-the-loop (HIL) tests show the hardware compatibility of the developed out-of-step algorithm. The proposed algorithm is also compared with recently reported algorithms. The comparison and test results on different large-scale systems show that the proposed algorithm is simple, fast, accurate, and HIL tested, and not affected by changes in power system parameters.https://doi.org/10.1186/s41601-021-00221-yClassificationDeep learningOut of Step DetectionPower swingWavelet transform |
| spellingShingle | Jigneshkumar Pramodbhai Desai Vijay Hiralal Makwana A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model Protection and Control of Modern Power Systems Classification Deep learning Out of Step Detection Power swing Wavelet transform |
| title | A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model |
| title_full | A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model |
| title_fullStr | A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model |
| title_full_unstemmed | A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model |
| title_short | A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model |
| title_sort | novel out of step relaying algorithm based on wavelet transform and a deep learning machine model |
| topic | Classification Deep learning Out of Step Detection Power swing Wavelet transform |
| url | https://doi.org/10.1186/s41601-021-00221-y |
| work_keys_str_mv | AT jigneshkumarpramodbhaidesai anoveloutofsteprelayingalgorithmbasedonwavelettransformandadeeplearningmachinemodel AT vijayhiralalmakwana anoveloutofsteprelayingalgorithmbasedonwavelettransformandadeeplearningmachinemodel AT jigneshkumarpramodbhaidesai noveloutofsteprelayingalgorithmbasedonwavelettransformandadeeplearningmachinemodel AT vijayhiralalmakwana noveloutofsteprelayingalgorithmbasedonwavelettransformandadeeplearningmachinemodel |