Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability

Liukai Chen; Lin Guan

doi:10.1186/s41601-023-00278-x

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability

Original Research | 更新时间：2026-09-30

- Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability
- Protection and Control of Modern Power Systems Vol. 8, Issue 1, Pages: 1-16(2023)
- 作者机构：
  
  School of Electric Power, South China University of Technology,Guangzhou,China
- 作者简介：
- 基金信息：
- DOI：10.1186/s41601-023-00278-x
  CLC：
- Published：01 January 2023
- 稿件说明：
移动端阅览
Liukai Chen, Lin Guan. Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability[J]. Protection and Control of Modern Power Systems, 2023, 8(1): 1-16.
DOI：

Liukai Chen, Lin Guan. Static information, K-neighbor, and self-attention aggregated scheme: a transient stability prediction model with enhanced interpretability[J]. Protection and Control of Modern Power Systems, 2023, 8(1): 1-16. DOI： 10.1186/s41601-023-00278-x.

摘要

Data-driven preventive scanning for transient stability assessment (DTSA) is a faster and more efficient solution than time-domain simulation (TDS). However

most current methods cannot balance generalization to different topologies and interpretability

with simple output. A model that conforms to the physical mechanism and richer label for transient stability can increase confidence in DTSA. Thus a static-information

k-neighbor

and self-attention aggregated schema (SKETCH) is proposed in this paper. Taking only static measurements as input

SKETCH gives several explanations that are consistent with the physical mechanisms of TSA and provides results for all generator stability while predicting system stability. A module based on the self-attention mechanism is designed to solve the locality problem of a graph neural network (GNN)

achieving subgraph equivalence outside the k-order neighborhood. Test re sults on the IEEE 39-bus system and IEEE 300-bus system indicate the superiority of SKETCH and also demonstrate the rich sample interpretation results. Highlights •A fast TSA scheme for pre-failure scanning. •A physical mechanism-based attention structure for dynamic graph pooling. •A node regression model that responds to key physical mechanisms. •Generator label for richer output information. •Top performance and post-hoc interpretation.

Abstract

Data-driven preventive scanning for transient stability assessment (DTSA) is a faster and more efficient solution than time-domain simulation (TDS). However

most current methods cannot balance generalization to different topologies and interpretability

with simple output. A model that conforms to the physical mechanism and richer label for transient stability can increase confidence in DTSA. Thus a static-information

k-neighbor

and self-attention aggregated schema (SKETCH) is proposed in this paper. Taking only static measurements as input

关键词

Keywords

references

1. Lv, J., Pawlak, M., Annakkage, U. D. ( 2017 ). Prediction of the transient stability boundary based on nonparametric additive modeling. IEEE Transactions on Power Systems , 32 ( 6 ), pp. 4362–4369. [Online ] . Available: https://doi.org/10.1109/TPWRS.2017.2669839.

2. Mazhari, S. M., Khorramdel, B., Chung, C. Y., Kamwa, I., Novosel, D. ( 2021 ). A Simulation-based classification approach for online prediction of generator dynamic behavior under multiple large disturbances. IEEE Transactions on Power Systems , 36 ( 2 ), pp. 1217–1228. [Online ] . Available: https://doi.org/10.1109/TPWRS.2020.3021137.

3. Zheng, C., Malbasa, V., Kezunovic, M. ( 2013 ). Regression tree for stability margin prediction using synchrophasor measurements. IEEE Transactions on Power Systems , 28 ( 2 ), pp. 1978–1987. [Online ] . Available: https://doi.org/10.1109/TPWRS.2012.2220988.

4. Liu, C., Sun, K., Rather, Z. H., Chen, Z., Bak, C. L., Thogersen, P., Lund, P. ( 2014 ). A systematic approach for dynamic security assessment and the corresponding preventive control scheme based on decision trees. IEEE Transactions on Power Systems , 29 ( 2 ), pp. 717–730. [Online ] . Available: https://doi.org/10.1109/TPWRS.2013.2283064.

5. Chen, M., Liu, Q., Chen, S., Liu, Y., Zhang, C. H., Liu, R. ( 2019 ). XGBoost-based algorithm interpretation and application on post-fault transient stability status prediction of power system. IEEE Access , 7, pp. 13149–13158. [Online ] . Available: https://doi.org/10.1109/ACCESS.2019.2893448.

6. Bellizio, F., Cremer, J. L., Sun, M., Strbac, G. ( 2021 ). A causality based feature selection approach for data-driven dynamic security assessment. Electric Power Systems Research , 201, p. 107537. [Online ] . Available: https://doi.org/10.10 16/j.epsr.2021.107537.

7. Chen, Q., Wang, H. ( 2021 ). Time-adaptive transient stability assessment based on gated recurrent unit. International Journal of Electrical Power and Energy Systems , 133, p. 107156. [Online ] . Available: https://doi.org/10.1016/j.ijepes.2021.107156.

8. Azman, M. S., Isbeih, Y. J., El Moursi, M. S., Elbassioni, K., Azman, S. K., Isbeih, Y. J., El Moursi, M. S., Elbassioni, K. ( 2020 ). A unified online deep learning prediction model for small signal and transient stability. IEEE Transactions on Power Systems , 35 ( 6 ), pp. 4585–4598. [Online ] . Available: https://doi.org/10.1109/TPWRS.2020.2999102.

9. Zhu, L., Hill, D. J., Lu, C. ( 2020 ). Hierarchical deep learning machine for power system online transient stability prediction. IEEE Transactions on Power Systems , 35 ( 3 ), pp. 2399–2411. [Online ] . Available: https://doi.org/10.1109/TPWRS.2019.2957377.

10. Gupta, A., Gurrala, G., Sastry, P. S. ( 2019 ). An online power system stability monitoring system using convolutional neural networks. IEEE Transactions on Power Systems , 34 ( 2 ), pp. 864–872. [Online ] . Available: https://doi.org/10.1109/TPWRS.2018.2872505.

11. Wang, Z., Zhou, Y., Guo, Q., Sun, H. ( 20 21 ). Interpretable neighborhood deep models for online total transfer capability evaluation of power systems. IEEE Transactions on Power Systems . [Online ] . Available: https://doi.org/10.1109/TPWRS.2021.3091710.

12. Ribeiro, M. T., Singh, S., Guestrin, C. ( 2016, 13–17-August ). “Why should I trust you?” Explaining the predictions of any classifier. In Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining , pp. 1135–1144. [Online ] . Available: https://doi.org/10.1145/2939672.2939778.

13. Huang, J., Guan, L., Su, Y., Yao, H., Guo, M., Zhong, Z. ( 2020 ). Recurrent graph convolutional network-based multi-task transient stability assessment framework in power system. IEEE Access , 8, pp. 93283–93296. [Online ] . Available: https://doi.org/10.1109/ACCESS.2020.2991263.

14. Huang, J., Guan, L., Su, Y., Yao, H., Guo, M., Zhong, Z. ( 2021 ). A topology adaptive high-speed transient stability assessment scheme based on multi-graph attention network with residual structure. International Journal of Electrical Power and Energy System . [Online ] . Available: https://doi.org/10.1016/j.ijepes.2021.106948.

16. Fahim, S. R., Sarker, S. K., Muyeen, S. M., Sheikh, M. R. I., Das, S. K., Simoes, M. ( 2021 ). A robust self-attentive capsule network for fault diagnosis of series-compensated transmission line. IEEE Transactions on Power Delivery , 36 ( 6 ), pp. 3846–3857. [Online ] . Available: https://doi.org/10.1109/TPWRD.2021.3049861.

20. Huang, J., Guan, L., Su, Y., Yao, H., Guo, M., Zhong, Z. ( 2021 ). System-scale-free transient contingency screening scheme based on steady-state information: A pooling-ensemble multi-graph learning approach. IEEE Transactions on Power Systems . [Online ] . Available: https://doi.org/10.1109/TPWRS.2021.3097331.

21. Zhou, J., Cui, G., Zhang, Z., Yong, C., Liu, Z., Wang, L., Li, C., Sun, M. ( 2019 ). Graph neural networks: A review of methods and applications. AI Open . [Online ] . Available: https://doi.org/10.1016/j.aiopen.2021.01.001.

23. Veličković, P., Casanova, A., Lió, P., Cucurull, G., Romero, A., Bengio, Y. ( 2018 ). Graph attention networks. In 6th International Conference on Learning Representations, ICLR 2018-Conference Track Proceedings , abs/1710.1, pp. 1–12. [Online ] . Available: https://doi.org/10.1007/978-3-031-01587-8_7.

24. Torch Contributors. ( 2019 ). PyTorch documentation-PyTorch 1.8.1 documentation . Torch Contributors. [Online ] . Available: https://pytorch.org/docs/stable/index.html, [Online ] . Available: https://pytorch.org/docs/1.8.1/.

25. PyG Team. (n.d.). PyG Documentation-pytorch_geometric 2.0.1 documentation . Retrieved October 20, 2021, from [Online ] . Available: https://pytorch-geometric.readthedocs.io/en/latest/.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Coordinated Control Strategy and Engineering Application of FSC-VSPSU in Generation State

Transient Stability Analysis and Coordinated Control Strategy of DC-Link Voltage for PLL-Based Grid-Connected DFIG System During Asymmetrical Grid Faults

An Interactive Operating Demand Response Approach for Hybrid Power Systems Integrating Renewable Energy Sources

Multi-Timescale Modeling and Dynamic Stability Analysis for Sustainable Microgrids: State-of-the-Art and Perspectives

Power quality enhancement in islanded microgrids via closed-loop adaptive virtual impedance control

Related Author

Huabo Shi

Yufei Teng

Zhaohua Hu

Gang Chen

Lijie Ding

Xueyang Zeng

Pengyu Pan

Baorui Chen

Related Institution

State Grid Sichuan Electric Power Research Institute

State Grid Sichuan Electric Power Company

State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University

Department of Electrical Engineering, National Institute of Technology, Patna

School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China

AI问答

⁰