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 50 条
  • [11] Embedding-Based Deep Neural Network and Convolutional Neural Network Graph Classifiers
    Elnaggar, Sarah G.
    Elsemman, Ibrahim E.
    Soliman, Taysir Hassan A.
    ELECTRONICS, 2023, 12 (12)
  • [12] Anomaly detection of traffic session based on graph neural network
    Du Peng
    Peng Cheng-Wei
    Xiang Peng
    Li Qing-Shan
    PROCEEDINGS OF THE 2022 INTERNATIONAL CONFERENCE ON CYBER SECURITY, CSW 2022, 2022, : 1 - 9
  • [13] Graph Neural Network Based Anomaly Detection in Dynamic Networks
    Guo J.-Y.
    Li R.-H.
    Zhang Y.
    Wang G.-R.
    Ruan Jian Xue Bao/Journal of Software, 2020, 31 (03): : 748 - 762
  • [14] Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes
    Sabokrou, Mohammad
    Fayyaz, Mohsen
    Fathy, Mahmood
    Moayed, Zahra
    Klette, Reinhard
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2018, 172 : 88 - 97
  • [15] Marrying Graph Kernel with Deep Neural Network: A Case Study for Network Anomaly Detection
    Yao, Yepeng
    Su, Liya
    Zhang, Chen
    Lu, Zhigang
    Liu, Baoxu
    COMPUTATIONAL SCIENCE - ICCS 2019, PT II, 2019, 11537 : 102 - 115
  • [16] Glaucoma Detection based on Deep Convolutional Neural Network
    Chen, Xiangyu
    Xu, Yanwu
    Wong, Damon Wing Kee
    Wong, Tien Yin
    Liu, Jiang
    2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2015, : 715 - 718
  • [17] Spacecraft Detection Based on Deep Convolutional Neural Network
    Yan, Zhenguo
    Song, Xin
    Zhong, Hanyang
    2018 IEEE 3RD INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP), 2018, : 148 - 153
  • [18] Acupoint Detection Based on Deep Convolutional Neural Network
    Sun, Lingyao
    Sun, Shiying
    Fu, Yuanbo
    Zhao, Xiaoguang
    PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE, 2020, : 7418 - 7422
  • [19] Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection
    Chen, Wenchao
    Tian, Long
    Chen, Bo
    Dai, Liang
    Duan, Zhibin
    Zhou, Mingyuan
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [20] Community detection based on BernNet graph convolutional neural network
    Hui Xie
    Yixin Ning
    Journal of the Korean Physical Society, 2023, 83 : 386 - 395