Multi-task transient stability adaptive assessment of power system based on MRSE-CNN

被引：0
作者：
Wu, Junyong [1 ]
Shi, Fashun [1 ]
Li, Lusu [1 ]
Zhao, Pengjie [2 ]
Zhang, Ruoyu [3 ]
机构：
[1] School of Electrical Engineering, Beijing Jiaotong University, Beijing
[2] State Grid Shanxi Electric Power Company, Taiyuan
[3] Institute of Science and Technology of China Three Gorges Corporation, Beijing
来源：
Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2025年 / 45卷 / 02期
关键词：
adaptive dynamic weight; critical clear time; transfer learning; transient power angle stability; transient stability assessment; transient voltage stability;
D O I：
10.16081/j.epae.202411016
中图分类号：
学科分类号：
摘要：
In order to solve the problems of insuffioient reliability and long time-consuming online update in the integrated assessment of transient power angle and transient voltage, a multi-task transient stability adaptive assessment method is proposed. The variable step size diehotomy method is used to construet the stable boundary of transient power angle and transient voltage from the time dimension. A multi-task convolutional neural network incorporating a multi-scale residual squeeze excitation mechanism is proposed, which is directly oriented to the measurement data and requires only three sampling points to complete the mapping between the input features and the stabilized boundaries, and realizes high-precision boundary fitting on the basis of guaranteeing the rapidity. The reliability of the model in practical application is further enhanced by introdueing the Huber loss function with adaptive dynamic weight. Adaptive updating of the model under three dimensions of load, topology, and renewable energy is realized by transfer learning when applied online. The validation results in an improved IEEE 39-bus system show that the proposed method not only balances the rapidity, accuracy and reliability, but also has the capability of fast updating under unknown scenarios. © 2025 Electric Power Automation Equipment Press. All rights reserved.
引用
收藏
页码：167 / 175
页数：8
相关论文
共 19 条
  • [1] World energy outlook 2019, (2019)
  • [2] MAO Anjia, Jing MA, KUAI Shengyu, Evolulion mechanism of transient and voltage stability for power system with high renewable penetration level [J], Proceedings of the CSEE, 40, 9, pp. 2745-2756, (2020)
  • [3] YE Mao, LIU Yan, GU Xueping, Et al., Calculation of dynamic wind power penetration limit considering System transient safety under background of blackout, Electric Power Automation Equipment, 38, 11, pp. 167-173, (2018)
  • [4] WANG Huaiyuan, CHEN Qifan, Transient stability assessment method of electric power systems based on stacked variational auto-encoder [J], Electric Power Automation Equipment, 39, 12, pp. 134-139, (2019)
  • [5] LIU Li, LI Yong, CAO Yijia, Et al., Transient rotor angle stability prediction method based on SVM and LSTM network, Electric Power Automation Equipment, 40, 2, pp. 129-139, (2020)
  • [6] WEI Zhinong, LI Chaofan, DING Aifei, Et al., Power System transient stability assessment based on Tri-lraining-SSAE semi supervised learning algorithm, Electric Power Automation Equipment, 43, 7, pp. 110-116, (2023)
  • [7] ZHU L P, HILL D J, LU C., Intelligent shorl-term vorläge stability assessment via spatial attention rectified RNN lear-ning[j], IEEE Transactions on Induslrial Informalics, 17, 10, pp. 7005-7016, (2021)
  • [8] HOU Jianlan, LIU Yuquan, XIE Xiaorong, Et al., Quantitative assessment index and method of transient voltage stability [jj, Electric Power Automation Equipment, 35, 10, pp. 151-156, (2015)
  • [9] JI Jiashen, WU Junyong, WANG Yanbo, Et al., Power System transient voltage stability assessment based on deep residual network[j], Power System Technology, 46, 7, pp. 2500-2511, (2022)
  • [10] ZHOU Ting, YANG Jun, ZHAN Xiangpeng, Data-driven method and inlerpretability analysis for transient voltage stability assessment[j], Power System Technology, 45, 11, pp. 4416-4425, (2021)
12