Graph attention convolution network for power flow calculation considering grid uncertainty
With the increasing penetration of renewable energy sources and the growing complexity of power system structures, the grid is increasingly impacted by both external and internal uncertainties. In this context, probabilistic power flow models based on artificial intelligence need to possess stronger...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | International Journal of Electrical Power & Energy Systems |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S014206152500064X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856940611010560 |
|---|---|
| author | Haochen Li Liqun Liu Shaojuan Yu Qiusheng He Qingfeng Wu Jianfeng Zhang Qinxiong Lu |
| author_facet | Haochen Li Liqun Liu Shaojuan Yu Qiusheng He Qingfeng Wu Jianfeng Zhang Qinxiong Lu |
| author_sort | Haochen Li |
| collection | DOAJ |
| description | With the increasing penetration of renewable energy sources and the growing complexity of power system structures, the grid is increasingly impacted by both external and internal uncertainties. In this context, probabilistic power flow models based on artificial intelligence need to possess stronger learning capabilities and robustness to handle the dynamic changes in the grid. To this end, this paper proposes a novel graph attention convolution model for real-time power flow calculation. Specifically, first, a multi-order hybrid adjacency matrix is constructed based on the impedance distance of the grid to fully reflect the underlying relationships between nodes. Second, a new correlation attention mechanism is developed to explore the correlations within the data. Meanwhile, inductive learning is used during node sampling to more efficiently utilize global information. Furthermore, the learning ability of the model is further enhanced by the combination of stacked dilated convolution layers and a fully connected layer. Finally, the model’s performance is tested on three different IEEE cases. The results show that, compared to the state-of-the-art methods, the proposed model not only achieves higher accuracy in predicting bus voltages and branch power but also demonstrates good robustness against uncertain topologies. |
| format | Article |
| id | doaj-art-d8400e8dc5a840eeb8091f05a3d0db38 |
| institution | Kabale University |
| issn | 0142-0615 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Electrical Power & Energy Systems |
| spelling | doaj-art-d8400e8dc5a840eeb8091f05a3d0db382025-02-12T05:29:22ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-04-01165110513Graph attention convolution network for power flow calculation considering grid uncertaintyHaochen Li0Liqun Liu1Shaojuan Yu2Qiusheng He3Qingfeng Wu4Jianfeng Zhang5Qinxiong Lu6School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024 China; Department of Electrical and Control Engineering, Shanxi Institute of Technology, Yangquan 045000 ChinaSchool of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024 China; Corresponding author.School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024 ChinaSchool of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024 ChinaSchool of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024 ChinaSchool of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024 ChinaSchool of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024 ChinaWith the increasing penetration of renewable energy sources and the growing complexity of power system structures, the grid is increasingly impacted by both external and internal uncertainties. In this context, probabilistic power flow models based on artificial intelligence need to possess stronger learning capabilities and robustness to handle the dynamic changes in the grid. To this end, this paper proposes a novel graph attention convolution model for real-time power flow calculation. Specifically, first, a multi-order hybrid adjacency matrix is constructed based on the impedance distance of the grid to fully reflect the underlying relationships between nodes. Second, a new correlation attention mechanism is developed to explore the correlations within the data. Meanwhile, inductive learning is used during node sampling to more efficiently utilize global information. Furthermore, the learning ability of the model is further enhanced by the combination of stacked dilated convolution layers and a fully connected layer. Finally, the model’s performance is tested on three different IEEE cases. The results show that, compared to the state-of-the-art methods, the proposed model not only achieves higher accuracy in predicting bus voltages and branch power but also demonstrates good robustness against uncertain topologies.http://www.sciencedirect.com/science/article/pii/S014206152500064XGrid uncertaintyProbabilistic power flowArtificial intelligenceGraph correlation attention mechanismDilated convolution |
| spellingShingle | Haochen Li Liqun Liu Shaojuan Yu Qiusheng He Qingfeng Wu Jianfeng Zhang Qinxiong Lu Graph attention convolution network for power flow calculation considering grid uncertainty International Journal of Electrical Power & Energy Systems Grid uncertainty Probabilistic power flow Artificial intelligence Graph correlation attention mechanism Dilated convolution |
| title | Graph attention convolution network for power flow calculation considering grid uncertainty |
| title_full | Graph attention convolution network for power flow calculation considering grid uncertainty |
| title_fullStr | Graph attention convolution network for power flow calculation considering grid uncertainty |
| title_full_unstemmed | Graph attention convolution network for power flow calculation considering grid uncertainty |
| title_short | Graph attention convolution network for power flow calculation considering grid uncertainty |
| title_sort | graph attention convolution network for power flow calculation considering grid uncertainty |
| topic | Grid uncertainty Probabilistic power flow Artificial intelligence Graph correlation attention mechanism Dilated convolution |
| url | http://www.sciencedirect.com/science/article/pii/S014206152500064X |
| work_keys_str_mv | AT haochenli graphattentionconvolutionnetworkforpowerflowcalculationconsideringgriduncertainty AT liqunliu graphattentionconvolutionnetworkforpowerflowcalculationconsideringgriduncertainty AT shaojuanyu graphattentionconvolutionnetworkforpowerflowcalculationconsideringgriduncertainty AT qiushenghe graphattentionconvolutionnetworkforpowerflowcalculationconsideringgriduncertainty AT qingfengwu graphattentionconvolutionnetworkforpowerflowcalculationconsideringgriduncertainty AT jianfengzhang graphattentionconvolutionnetworkforpowerflowcalculationconsideringgriduncertainty AT qinxionglu graphattentionconvolutionnetworkforpowerflowcalculationconsideringgriduncertainty |