Data-driven small signal stability assessment of power system
In this article, we focus on the data-driven approach. The experimental data comes from the New England 10-machine 39-bus system. The data-driven method needs to obtain a regression model in the training phase and then use the regression model to get the predicted value in the test phase to evaluate...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/153320 |
| _version_ | 1826117791260868608 |
|---|---|
| author | Luo, Bingqian |
| author2 | Xu Yan |
| author_facet | Xu Yan Luo, Bingqian |
| author_sort | Luo, Bingqian |
| collection | NTU |
| description | In this article, we focus on the data-driven approach. The experimental data comes from the New England 10-machine 39-bus system. The data-driven method needs to obtain a regression model in the training phase and then use the regression model to get the predicted value in the test phase to evaluate the regression performance. We use the Gaussian regression model in this article. Therefore, we have discussed the Bayesian inference, Gaussian process, Gaussian distribution, and Gaussian noise involved in the Gaussian regression model. We use principal component analysis and Relief’s method to perform data dimensionality reduction processing on input features. Finally, we also compared the best performing Gaussian regression model with other algorithms. Other algorithms include the Extreme Learning Machine, Random Vector Functional Link, Artificial Neural Networks, and Random Forest. By comparison, we know that Gaussian distribution has better regression performance. Finally, we discussed the deficiencies of this paper and future research topics worthy of attention in the field of small-signal stability. |
| first_indexed | 2024-10-01T04:33:07Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/153320 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:33:07Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1533202023-07-04T16:12:25Z Data-driven small signal stability assessment of power system Luo, Bingqian Xu Yan School of Electrical and Electronic Engineering xuyan@ntu.edu.sg Engineering::Electrical and electronic engineering In this article, we focus on the data-driven approach. The experimental data comes from the New England 10-machine 39-bus system. The data-driven method needs to obtain a regression model in the training phase and then use the regression model to get the predicted value in the test phase to evaluate the regression performance. We use the Gaussian regression model in this article. Therefore, we have discussed the Bayesian inference, Gaussian process, Gaussian distribution, and Gaussian noise involved in the Gaussian regression model. We use principal component analysis and Relief’s method to perform data dimensionality reduction processing on input features. Finally, we also compared the best performing Gaussian regression model with other algorithms. Other algorithms include the Extreme Learning Machine, Random Vector Functional Link, Artificial Neural Networks, and Random Forest. By comparison, we know that Gaussian distribution has better regression performance. Finally, we discussed the deficiencies of this paper and future research topics worthy of attention in the field of small-signal stability. Master of Science (Power Engineering) 2021-11-18T06:54:43Z 2021-11-18T06:54:43Z 2021 Thesis-Master by Coursework Luo, B. (2021). Data-driven small signal stability assessment of power system. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153320 https://hdl.handle.net/10356/153320 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Luo, Bingqian Data-driven small signal stability assessment of power system |
| title | Data-driven small signal stability assessment of power system |
| title_full | Data-driven small signal stability assessment of power system |
| title_fullStr | Data-driven small signal stability assessment of power system |
| title_full_unstemmed | Data-driven small signal stability assessment of power system |
| title_short | Data-driven small signal stability assessment of power system |
| title_sort | data driven small signal stability assessment of power system |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/153320 |
| work_keys_str_mv | AT luobingqian datadrivensmallsignalstabilityassessmentofpowersystem |