Anomaly detection based on a deep graph convolutional neural network for reliability improvement

被引:0
作者
Xu, Gang [1 ]
Hu, Jie [1 ]
Qie, Xin [1 ]
Rong, Jingguo [2 ]
机构
[1] North China Elect Power Univ, Sch Elect & Elect Engn, Beijing, Peoples R China
[2] State Grid Econ & Technol Res Inst Co Ltd, Beijing, Peoples R China
关键词
reliability improvement; graph convolutional network; anomaly detection; skip connection mechanism; artificial intelligence;
D O I
10.3389/fenrg.2024.1345361
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Effective anomaly detection in power grid engineering is essential for ensuring the reliability of dispatch and operation. Traditional anomaly detection methods based on manual review and expert experience cannot be adapted to the current rapid increases in project data. In this work, to address this issue, knowledge graph technology is used to build an anomaly detection dataset. Considering the over-smoothing problem associated with multi-level GCN networks, a deep skip connection framework for anomaly detection on attributed networks called DIET is proposed for anomaly detection on ultra-high voltage (UHV) projects. Furthermore, a distance-based object function is added to the conventional object function, which gives DIET the ability to process multiple attributes of the same type. Several comparative experiments are conducted using five state-of-the-art algorithms. The results of the receiver operating characteristic with the area under the curve (ROC-AUC) indicator show a 12% minimum improvement over other methods. Other evaluation indicators such as precision@K and recall@K indicate that DIET can achieve a better detection rate with less ranking. To evaluate the feasibility of the proposed model, a parameter analysis of the number of GCN layers is also performed. The results show that relatively few layers are needed to achieve good results with small datasets.
引用
收藏
页数:14
相关论文
共 33 条
[1]   Natural Disasters, Economic Growth, and Carbon Emissions: Empirical Analysis of Chinese Data Based on a Nonlinear Auto-Regressive Distributed Lag Model [J].
Cao, Ming ;
Xu, Yiming ;
Sun, Yuanhong ;
Cang, Dingbang .
SUSTAINABILITY, 2023, 15 (21)
[2]  
[陈立帆 Chen Lifan], 2023, [电网技术, Power System Technology], V47, P2549
[3]  
Ding K, 2019, Data Min, P594
[4]  
Fan HY, 2020, INT CONF ACOUST SPEE, P5685, DOI [10.1109/ICASSP40776.2020.9053387, 10.1109/icassp40776.2020.9053387]
[5]  
[郭榕 Guo Rong], 2021, [电网技术, Power System Technology], V45, P2092
[6]  
Hong Y., 2014, Design and implementation of Fujian power transmission project design review system
[7]  
Huang J., 2018, Mod. Electron. Tech, V41, P112, DOI [10.16652/j.issn.1004-373x.2018.04.028, DOI 10.16652/J.ISSN.1004-373X.2018.04.028]
[8]  
Huang WB, 2022, Arxiv, DOI arXiv:2008.09864
[9]   A Survey on Knowledge Graphs: Representation, Acquisition, and Applications [J].
Ji, Shaoxiong ;
Pan, Shirui ;
Cambria, Erik ;
Marttinen, Pekka ;
Yu, Philip S. .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (02) :494-514
[10]   Semi-supervised Anomaly Detection on Attributed Graphs [J].
Kumagai, Atsutoshi ;
Iwata, Tomoharu ;
Fujiwara, Yasuhiro .
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,