Research on Transient Stability Assessment Method of Power System Based on Improved Long Short Term Memory Network

被引：0

作者：

Xie Z. ^{[1
]}

Zhang D. ^{[1
,2
]}

Han X. ^{[1
]}

Hu W. ^{[3
]}

机构：

[1] Shanxi Key Laboratory of Power System Operation and Control, Taiyuan University of Technology, Shanxi Province, Taiyuan

[2] China Electric Power Research Institute, Haidian District, Beijing

[3] State Key Lab of Control and Simulation of Power Systems and Generation Equipments, Department of Electrical Engineering, Tsinghua University, Haidian District, Beijing

来源：

Dianwang Jishu/Power System Technology | 2024年 / 48卷 / 03期

关键词：

attention; long short term memory network; transferring learning; transient stability assessment; unbalance sample;

D O I：

10.13335/j.1000-3673.pst.2023.1482

中图分类号：

学科分类号：

摘要：

The massive measurement data of modern power systems offer a trustworthy database for the transient stability assessment of power systems. At the same time, data and information mining have become the research focus. It’s still necessary to further investigate the information in unbalanced fault samples and multi-characteristic electrical time series data. To fully mine the information contained in the transient stability assessment samples, a long short term memory network combined with an attention mechanism (LSTMA) method is proposed in this paper. The long short term memory network is used as the fundamental classifier in the offline training process, and the attention mechanism is introduced to help the classifier learn the salient characteristics of the samples. Additionally, the loss function is modified to enhance the ability to identify unbalanced samples. The target domain in online applications is small. In online applications, the offline LSTMA model is updated using the transfer learning method, and the impacts of different transfer learning approaches on model performance are contrasted. The transfer learning strategy determination method promotes quick decision-making in practical applications. Experiments are carried out on IEEE 39-node and IEEE 300-node systems to verify the effectiveness of the proposed method. © 2024 Power System Technology Press. All rights reserved.

引用

页码：998 / 1007

页数：9

共 27 条

[1] MAO Anjia, MA Jing, KUAI Shengyu, Et al., Evolution mechanism of transient and voltage stability for power system with high renewable penetration level, Proceedings of the CSEE, 40, 9, pp. 2745-2755, (2020)
[2] KANG Chongqing, YAO Liangzhong, Key scientific issues and theoretical research framework for power systems with high proportion of renewable energy, Automation of Electric Power Systems, 41, 9, pp. 1-11, (2017)
[3] KANG Chongqing, DU Ershun, GUO Hongye, Et al., Primary exploration of six essential factors in new power system, Power System Technology, 47, 5, pp. 1741-1750, (2023)
[4] HU Wei, ZHENG Le, MIN Yong, Et al., Research on power system transient stability assessment based on deep learning of big data technique, Power System Technology, 41, 10, pp. 3140-3146, (2017)
[5] ZHOU Zihan, BU Guangquan, MA Shicong, Et al., Assessment and optimization of power system transient stability based on feature-separated neural networks, Power System Technology, 45, 9, pp. 3658-3666, (2021)
[6] ZHANG Weiling, HU Wei, MIN Yong, Et al., Conservative online transient stability assessment in power system based on concept of stability region, Power System Technology, 40, 4, pp. 992-998, (2016)
[7] WANG Tong, LIU Jiuliang, ZHU Shaoxuan, Et al., Transient stability assessment and emergency control strategy based on random forest in power system, Power System Technology, 44, 12, pp. 4694-4701, (2020)
[8] BENGIO Y., Learning deep architectures for AI[J], Foundations and Trends® in Machine Learning, 2, 1, pp. 1-127, (2009)
[9] (2020)
[10] SHI Fashun, WU Junyong, WU Haoyan, Et al., Integrated evaluation of power system transient power angle and transient voltage stability margin based on deep learning, Power System Technology, 47, 2, pp. 731-740, (2023)

← 1 2 3 →