A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional network
Security-constrained unit commitment (SCUC) is of great importance for the economic and reliable operation of the power system. The computational hardness of SCUC remains a significant issue in the power system and electricity market operations, especially with the rapid expansion of the power syste...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | International Journal of Electrical Power & Energy Systems |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0142061524005453 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595386844315648 |
|---|---|
| author | Liqian Gao Lishen Wei Shichang Cui Jiakun Fang Xiaomeng Ai Wei Yao Jinyu Wen |
| author_facet | Liqian Gao Lishen Wei Shichang Cui Jiakun Fang Xiaomeng Ai Wei Yao Jinyu Wen |
| author_sort | Liqian Gao |
| collection | DOAJ |
| description | Security-constrained unit commitment (SCUC) is of great importance for the economic and reliable operation of the power system. The computational hardness of SCUC remains a significant issue in the power system and electricity market operations, especially with the rapid expansion of the power system, leading to increased challenges of obtaining a high-quality solution in a fast way. In this sense, this paper proposes a topology-guided high-quality solution learning framework based on graph convolutional network (GCN) and neighborhood search (NS). Firstly, a GCN-based method is presented to learn the potential patterns between commitments and graph data associated with bus feature and power grid topology. Secondly, an adaptive threshold-based method is designed to fix binary variables to achieve model reduction. Thirdly, a customized prediction-based NS is developed to restore the feasibility of the predicted commitment. Case studies with different scales verify the effectiveness and efficiency of the proposed framework for SCUC. Compared with other methods, it demonstrates the superiority of learning based on power grid graph data. In the end, it can be concluded that the feasibility and high-quality of the solution can be guaranteed while reducing most of the computation time. |
| format | Article |
| id | doaj-art-3ae8ccd88b6e4016b04aadaf392f5f0e |
| institution | Kabale University |
| issn | 0142-0615 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Electrical Power & Energy Systems |
| spelling | doaj-art-3ae8ccd88b6e4016b04aadaf392f5f0e2025-01-19T06:23:49ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-03-01164110322A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional networkLiqian Gao0Lishen Wei1Shichang Cui2Jiakun Fang3Xiaomeng Ai4Wei Yao5Jinyu Wen6State Key Laboratory of Advanced Electromagnetic Technology (Huazhong University of Science and Technology), Wuhan 430074, ChinaState Key Laboratory of Advanced Electromagnetic Technology (Huazhong University of Science and Technology), Wuhan 430074, ChinaState Key Laboratory of Advanced Electromagnetic Technology (Huazhong University of Science and Technology), Wuhan 430074, ChinaState Key Laboratory of Advanced Electromagnetic Technology (Huazhong University of Science and Technology), Wuhan 430074, ChinaCorresponding author.; State Key Laboratory of Advanced Electromagnetic Technology (Huazhong University of Science and Technology), Wuhan 430074, ChinaState Key Laboratory of Advanced Electromagnetic Technology (Huazhong University of Science and Technology), Wuhan 430074, ChinaState Key Laboratory of Advanced Electromagnetic Technology (Huazhong University of Science and Technology), Wuhan 430074, ChinaSecurity-constrained unit commitment (SCUC) is of great importance for the economic and reliable operation of the power system. The computational hardness of SCUC remains a significant issue in the power system and electricity market operations, especially with the rapid expansion of the power system, leading to increased challenges of obtaining a high-quality solution in a fast way. In this sense, this paper proposes a topology-guided high-quality solution learning framework based on graph convolutional network (GCN) and neighborhood search (NS). Firstly, a GCN-based method is presented to learn the potential patterns between commitments and graph data associated with bus feature and power grid topology. Secondly, an adaptive threshold-based method is designed to fix binary variables to achieve model reduction. Thirdly, a customized prediction-based NS is developed to restore the feasibility of the predicted commitment. Case studies with different scales verify the effectiveness and efficiency of the proposed framework for SCUC. Compared with other methods, it demonstrates the superiority of learning based on power grid graph data. In the end, it can be concluded that the feasibility and high-quality of the solution can be guaranteed while reducing most of the computation time.http://www.sciencedirect.com/science/article/pii/S0142061524005453Security-constrained unit commitmentGraph convolutional networkNeighborhood search |
| spellingShingle | Liqian Gao Lishen Wei Shichang Cui Jiakun Fang Xiaomeng Ai Wei Yao Jinyu Wen A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional network International Journal of Electrical Power & Energy Systems Security-constrained unit commitment Graph convolutional network Neighborhood search |
| title | A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional network |
| title_full | A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional network |
| title_fullStr | A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional network |
| title_full_unstemmed | A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional network |
| title_short | A topology-guided high-quality solution learning framework for security-constraint unit commitment based on graph convolutional network |
| title_sort | topology guided high quality solution learning framework for security constraint unit commitment based on graph convolutional network |
| topic | Security-constrained unit commitment Graph convolutional network Neighborhood search |
| url | http://www.sciencedirect.com/science/article/pii/S0142061524005453 |
| work_keys_str_mv | AT liqiangao atopologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT lishenwei atopologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT shichangcui atopologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT jiakunfang atopologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT xiaomengai atopologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT weiyao atopologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT jinyuwen atopologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT liqiangao topologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT lishenwei topologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT shichangcui topologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT jiakunfang topologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT xiaomengai topologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT weiyao topologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork AT jinyuwen topologyguidedhighqualitysolutionlearningframeworkforsecurityconstraintunitcommitmentbasedongraphconvolutionalnetwork |