Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch
Abstract High penetrations of renewable energy are crucial for low‐carbon power systems. However, the higher volatility of renewable power generation pushes real‐time operations closer to equipment limits. It is thus important to utilize flexibilities in the system through corrective security‐constr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-02-01
|
| Series: | IET Renewable Power Generation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rpg2.12830 |
| _version_ | 1797295096871256064 |
|---|---|
| author | Yaowen Yu Yijie Gao Yuanzheng Li Ying Yan |
| author_facet | Yaowen Yu Yijie Gao Yuanzheng Li Ying Yan |
| author_sort | Yaowen Yu |
| collection | DOAJ |
| description | Abstract High penetrations of renewable energy are crucial for low‐carbon power systems. However, the higher volatility of renewable power generation pushes real‐time operations closer to equipment limits. It is thus important to utilize flexibilities in the system through corrective security‐constrained economic dispatch (SCED) that allows generators to take corrective adjustments after contingencies. The corrective SCED problem, containing a large number of contingencies, and corresponding post‐contingency decisions and constraints, is very large in scale and difficult to solve using purely model‐based methods within the strict time limits of real‐time markets. To accelerate the solution process, this paper develops a novel interpretable data‐driven contingency classification method. Historical data and their potentially useful patterns are utilized in interpretable data‐driven decision tree classifiers. To directly consider continuous features, such as net load values, and to consider imbalanced datasets without much additional complexity, Improved Strong Optimal Classification Trees (ISOCTs) are developed with new branching threshold constraints and category weights in the objective function. ISOCTs are then embedded into a hybrid model‐based and data‐driven framework to guarantee the accuracy of the real‐time active contingency set and the resulting security of dispatch decisions. Numerical testing results demonstrate the classification accuracy, computational efficiency, and interpretability of the proposed approach. |
| first_indexed | 2024-03-07T21:41:49Z |
| format | Article |
| id | doaj.art-a6a5eff010f3456b91d66115ae672a38 |
| institution | Directory Open Access Journal |
| issn | 1752-1416 1752-1424 |
| language | English |
| last_indexed | 2024-03-07T21:41:49Z |
| publishDate | 2024-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Renewable Power Generation |
| spelling | doaj.art-a6a5eff010f3456b91d66115ae672a382024-02-26T08:05:21ZengWileyIET Renewable Power Generation1752-14161752-14242024-02-0118348950110.1049/rpg2.12830Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatchYaowen Yu0Yijie Gao1Yuanzheng Li2Ying Yan3School of Artificial Intelligence and Automation, The Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan ChinaSchool of Artificial Intelligence and Automation, The Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan ChinaSchool of Artificial Intelligence and Automation, The Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan ChinaC‐MEIC, CICAEET, School of AutomationNanjing University of Information Science and TechnologyNanjing ChinaAbstract High penetrations of renewable energy are crucial for low‐carbon power systems. However, the higher volatility of renewable power generation pushes real‐time operations closer to equipment limits. It is thus important to utilize flexibilities in the system through corrective security‐constrained economic dispatch (SCED) that allows generators to take corrective adjustments after contingencies. The corrective SCED problem, containing a large number of contingencies, and corresponding post‐contingency decisions and constraints, is very large in scale and difficult to solve using purely model‐based methods within the strict time limits of real‐time markets. To accelerate the solution process, this paper develops a novel interpretable data‐driven contingency classification method. Historical data and their potentially useful patterns are utilized in interpretable data‐driven decision tree classifiers. To directly consider continuous features, such as net load values, and to consider imbalanced datasets without much additional complexity, Improved Strong Optimal Classification Trees (ISOCTs) are developed with new branching threshold constraints and category weights in the objective function. ISOCTs are then embedded into a hybrid model‐based and data‐driven framework to guarantee the accuracy of the real‐time active contingency set and the resulting security of dispatch decisions. Numerical testing results demonstrate the classification accuracy, computational efficiency, and interpretability of the proposed approach.https://doi.org/10.1049/rpg2.12830artificial intelligencedecision treespower generation dispatchpower system securityrenewable energy sources |
| spellingShingle | Yaowen Yu Yijie Gao Yuanzheng Li Ying Yan Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch IET Renewable Power Generation artificial intelligence decision trees power generation dispatch power system security renewable energy sources |
| title | Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch |
| title_full | Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch |
| title_fullStr | Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch |
| title_full_unstemmed | Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch |
| title_short | Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch |
| title_sort | interpretable data driven contingency classification for real time corrective security constrained economic dispatch |
| topic | artificial intelligence decision trees power generation dispatch power system security renewable energy sources |
| url | https://doi.org/10.1049/rpg2.12830 |
| work_keys_str_mv | AT yaowenyu interpretabledatadrivencontingencyclassificationforrealtimecorrectivesecurityconstrainedeconomicdispatch AT yijiegao interpretabledatadrivencontingencyclassificationforrealtimecorrectivesecurityconstrainedeconomicdispatch AT yuanzhengli interpretabledatadrivencontingencyclassificationforrealtimecorrectivesecurityconstrainedeconomicdispatch AT yingyan interpretabledatadrivencontingencyclassificationforrealtimecorrectivesecurityconstrainedeconomicdispatch |