Intelligent identification method of power grid fault events considering sample classification imbalance

被引：0

作者：

Wei Z. ^{[1
]}

Shi D. ^{[1
]}

Zhang M. ^{[2
]}

Sun G. ^{[1
]}

Zang H. ^{[1
]}

Shen P. ^{[2
]}

机构：

[1] College of Energy and Electrical Engineering, Hohai University, Nanjing

[2] Nanjing Power Supply Company of State Grid Jiangsu Electric Power Co., Ltd., Nanjing

来源：

Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2021年 / 41卷 / 11期

关键词：

Classification imbalance; Cost-sensitive learning; Deep learning; Identification of power grid fault events; Model fusion;

D O I：

10.16081/j.epae.202107019

中图分类号：

学科分类号：

摘要：

In order to solve the problem that the difference of the failure probability of different equipments in the power grid affects the accuracy of fault intelligent diagnosis technology, an intelligent identification method of power grid fault events based on cost-sensitive learning and model adaptive selection fusion is proposed. Firstly, the Word2vec model is used to vectorize the pre-processed power grid alarm information, and two bidirectional long-short-term memory networks are established as basic classification models. Then, the cost-sensitive loss function is designed. The cross-entropy loss function and cost-sensitive loss function are respectively applied to the two classification models. Finally, a model adaptive selection fusion method is proposed to fuse the above classification models, so as to obtain the identification results of fault events. Actual data test shows that the proposed method can effectively reduce the impact of sample classification imbalance in the fault event identification. © 2021, Electric Power Automation Equipment Press. All right reserved.

引用

页码：93 / 99

页数：6

共 20 条

[1] SUN Guoqiang, SHEN Peifeng, ZHAO Yang, Et al., Intelligent recognition of power grid monitoring alarm event combining knowledge base and deep learning, Electric Power Automation Equipment, 40, 4, pp. 40-47, (2020)
[2] WANG Cuiyang, JIANG Quanyuan, TANG Yajie, Et al., Fault diagnosis of power dispatching based on alarm signal text mining, Electric Power Automation Equipment, 39, 4, pp. 126-132, (2019)
[3] LI Yuancheng, ZENG Jing, Detection method of false data injection attack on power grid based on improved convolutional neural network, Automation of Electric Power Systems, 43, 20, pp. 97-104, (2019)
[4] SUN Lixia, BAI Jingtao, ZHOU Zhaoyu, Et al., Transient stability assessment of power system based on bi-directional long-short-term memory network, Automation of Electric Power Systems, 44, 13, pp. 64-72, (2020)
[5] XIE Hua, CHEN Junxing, ZHAO Yuming, Et al., Knowledge acquisition method of power transformer condition assessment based on SMOTE and decision tree algorithm, Electric Po-wer Automation Equipment, 40, 2, pp. 137-142, (2020)
[6] LI Yaxin, HOU Huijuan, XU Mingkai, Et al., Oil chromatogram case generation method of transformer based on policy gradient and generative adversarial networks, Electric Power Automation Equipment, 40, 12, pp. 211-218, (2020)
[7] TAN Lintao, LI Junliang, REN Bing, Et al., Health evaluation model of smart grid dispatch and control system based on RB-XGBoost algorithm, Electric Power Automation Equipment, 40, 2, pp. 189-198, (2020)
[8] ZHANG Zhongliang, LUO Xinggang, GARCIA S, Et al., Cost-sensitive back-propagation neural networks with binarization tech-niques in addressing multi-class problems and non-competent classifiers, Applied Soft Computing, 56, pp. 357-367, (2017)
[9] BRADFORD J P, KUNZ C, KOHAVI R, Et al., Pruning decision trees with misclassification costs, Proceedings of the 10th European Conference on Machine Learning, pp. 131-136, (1998)
[10] HUANG Haisong, WEI Jian'an, KANG Peidong, New over-sampling SVM classiﬁcation algorithm based on unbalanced data sample characteristics, Control and Decision, 33, 9, pp. 1549-1558, (2018)

← 1 2 →