Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies
Dynamic State Estimation is a crucial task in power systems. Graph Neural Networks have demonstrated significant potential in dynamic state estimation, for power systems by effectively analyzing measurement data and capturing the complex interactions and interrelations among the measurements through...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Access Journal of Power and Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11105082/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850034418622660608 |
|---|---|
| author | Seyed Hamed Haghshenas Mia Naeini |
| author_facet | Seyed Hamed Haghshenas Mia Naeini |
| author_sort | Seyed Hamed Haghshenas |
| collection | DOAJ |
| description | Dynamic State Estimation is a crucial task in power systems. Graph Neural Networks have demonstrated significant potential in dynamic state estimation, for power systems by effectively analyzing measurement data and capturing the complex interactions and interrelations among the measurements through the system’s graph structure. However, the information about the system’s graph structure may be inaccurate due to noise, attack or lack of accurate information about the topology of the system. This paper studies these scenarios under topology uncertainties and evaluates the impact of the topology uncertainties on the performance of a Temporal Graph Convolutional Network (TGCN) for state estimation in power systems. In order to make the model resilient to topology uncertainties, modifications in the TGCN model are proposed to incorporate a knowledge graph, generated based on the measurement data. This knowledge graph supports the assumed uncertain system graph. Two variations of the TGCN architecture are introduced to integrate the knowledge graph, and their performances are evaluated and compared to demonstrate improved resilience against topology uncertainties. The evaluation results indicate that while the two proposed architecture show different performance, they preserve and improve the performance of the TGCN state estimation under topology uncertainties. |
| format | Article |
| id | doaj-art-810b7ec1877645fe803f8d6aa26e2bd3 |
| institution | DOAJ |
| issn | 2687-7910 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Access Journal of Power and Energy |
| spelling | doaj-art-810b7ec1877645fe803f8d6aa26e2bd32025-08-20T02:57:51ZengIEEEIEEE Open Access Journal of Power and Energy2687-79102025-01-011252954010.1109/OAJPE.2025.359427611105082Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology InaccuraciesSeyed Hamed Haghshenas0https://orcid.org/0000-0002-7670-6582Mia Naeini1https://orcid.org/0000-0002-7292-8524Department of Electrical Engineering, University of South Florida, Tampa, FL, USADepartment of Electrical Engineering, University of South Florida, Tampa, FL, USADynamic State Estimation is a crucial task in power systems. Graph Neural Networks have demonstrated significant potential in dynamic state estimation, for power systems by effectively analyzing measurement data and capturing the complex interactions and interrelations among the measurements through the system’s graph structure. However, the information about the system’s graph structure may be inaccurate due to noise, attack or lack of accurate information about the topology of the system. This paper studies these scenarios under topology uncertainties and evaluates the impact of the topology uncertainties on the performance of a Temporal Graph Convolutional Network (TGCN) for state estimation in power systems. In order to make the model resilient to topology uncertainties, modifications in the TGCN model are proposed to incorporate a knowledge graph, generated based on the measurement data. This knowledge graph supports the assumed uncertain system graph. Two variations of the TGCN architecture are introduced to integrate the knowledge graph, and their performances are evaluated and compared to demonstrate improved resilience against topology uncertainties. The evaluation results indicate that while the two proposed architecture show different performance, they preserve and improve the performance of the TGCN state estimation under topology uncertainties.https://ieeexplore.ieee.org/document/11105082/Graph topology noisesmart gridsdynamic state estimationforecasting-aided state estimation graph neural networks |
| spellingShingle | Seyed Hamed Haghshenas Mia Naeini Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies IEEE Open Access Journal of Power and Energy Graph topology noise smart grids dynamic state estimation forecasting-aided state estimation graph neural networks |
| title | Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies |
| title_full | Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies |
| title_fullStr | Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies |
| title_full_unstemmed | Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies |
| title_short | Resilient Temporal Graph Convolutional Network for Smart Grid State Estimation Under Topology Inaccuracies |
| title_sort | resilient temporal graph convolutional network for smart grid state estimation under topology inaccuracies |
| topic | Graph topology noise smart grids dynamic state estimation forecasting-aided state estimation graph neural networks |
| url | https://ieeexplore.ieee.org/document/11105082/ |
| work_keys_str_mv | AT seyedhamedhaghshenas resilienttemporalgraphconvolutionalnetworkforsmartgridstateestimationundertopologyinaccuracies AT mianaeini resilienttemporalgraphconvolutionalnetworkforsmartgridstateestimationundertopologyinaccuracies |