The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization
With the increasing uncertainty of the generation, transmission, and consumption sides in new power systems, the complexity and scale of power system topology relationship are continuously growing. Conventional data analysis methods for Euclidean space often exhibit poor performance and low accuracy...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
State Grid Energy Research Institute
2024-12-01
|
| Series: | Zhongguo dianli |
| Subjects: | |
| Online Access: | https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202410093 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850038018401894400 |
|---|---|
| author | Zhuo LI Yinzhe WANG Lin YE Yadi LUO Xuri SONG Zhenyu ZHANG |
| author_facet | Zhuo LI Yinzhe WANG Lin YE Yadi LUO Xuri SONG Zhenyu ZHANG |
| author_sort | Zhuo LI |
| collection | DOAJ |
| description | With the increasing uncertainty of the generation, transmission, and consumption sides in new power systems, the complexity and scale of power system topology relationship are continuously growing. Conventional data analysis methods for Euclidean space often exhibit poor performance and low accuracy when representing the topological structures relationship with multi-source heterogeneous and irregular characteristics. Graph Neural Networks (GNNs) are capable of capturing complex dependency relationship between different nodes and edges, and effectively mining spatiotemporal features in non-Euclidean data structures, are therefore suitable for the perception and modeling of complex power system topologies. In this context, this paper builds upon previous research progress, providing the definition and characteristics of GNNs, and discussing the unique features and advantages of different variants GNNs. After that, it summarizes the current applications of GNNs in power system state perception, prediction, and graph-based power flow calculation, aiming to explore the suitability of GNNs for new power systems from the perception-prediction-optimization perspectives. Finally, a summary and outlook on the potential challenges and future development directions for GNNs are provided. |
| format | Article |
| id | doaj-art-bf078648c25045d08f25a5353f8a4440 |
| institution | DOAJ |
| issn | 1004-9649 |
| language | zho |
| publishDate | 2024-12-01 |
| publisher | State Grid Energy Research Institute |
| record_format | Article |
| series | Zhongguo dianli |
| spelling | doaj-art-bf078648c25045d08f25a5353f8a44402025-08-20T02:56:43ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492024-12-01571221610.11930/j.issn.1004-9649.202410093zgdl-57-12-lizhuoThe Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-OptimizationZhuo LI0Yinzhe WANG1Lin YE2Yadi LUO3Xuri SONG4Zhenyu ZHANG5College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing 100083, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing 100083, ChinaChina Electric Power Research Institute, Beijing 100192, ChinaChina Electric Power Research Institute, Beijing 100192, ChinaState Grid National Power Dispatching and Control Center, Beijing 100031, ChinaWith the increasing uncertainty of the generation, transmission, and consumption sides in new power systems, the complexity and scale of power system topology relationship are continuously growing. Conventional data analysis methods for Euclidean space often exhibit poor performance and low accuracy when representing the topological structures relationship with multi-source heterogeneous and irregular characteristics. Graph Neural Networks (GNNs) are capable of capturing complex dependency relationship between different nodes and edges, and effectively mining spatiotemporal features in non-Euclidean data structures, are therefore suitable for the perception and modeling of complex power system topologies. In this context, this paper builds upon previous research progress, providing the definition and characteristics of GNNs, and discussing the unique features and advantages of different variants GNNs. After that, it summarizes the current applications of GNNs in power system state perception, prediction, and graph-based power flow calculation, aiming to explore the suitability of GNNs for new power systems from the perception-prediction-optimization perspectives. Finally, a summary and outlook on the potential challenges and future development directions for GNNs are provided.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202410093new power systemsuncertaintygraph neural networksstate perceptionpredictiongraph-based power flow calculation |
| spellingShingle | Zhuo LI Yinzhe WANG Lin YE Yadi LUO Xuri SONG Zhenyu ZHANG The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization Zhongguo dianli new power systems uncertainty graph neural networks state perception prediction graph-based power flow calculation |
| title | The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization |
| title_full | The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization |
| title_fullStr | The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization |
| title_full_unstemmed | The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization |
| title_short | The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization |
| title_sort | application of graph neural networks in power systems from perspective of perception prediction optimization |
| topic | new power systems uncertainty graph neural networks state perception prediction graph-based power flow calculation |
| url | https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202410093 |
| work_keys_str_mv | AT zhuoli theapplicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT yinzhewang theapplicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT linye theapplicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT yadiluo theapplicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT xurisong theapplicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT zhenyuzhang theapplicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT zhuoli applicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT yinzhewang applicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT linye applicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT yadiluo applicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT xurisong applicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization AT zhenyuzhang applicationofgraphneuralnetworksinpowersystemsfromperspectiveofperceptionpredictionoptimization |