Graph neural network approach for anomaly detection. (August 2021)

• Record Type: Journal Article
• Authors: Xie, Lingqiang; Pi, Dechang; Zhang, Xiangyan; Chen, Junfu; Luo, Yi; Yu, Wen
• Is Part Of: Measurement. Volume 180(2021)
• Publication Date: 2021-08
• Subjects: Telemetry data -- Graph neural network -- Dynamic threshold -- Anomaly detection; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.109546
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Take the lead in using GNN to complete the task of anomaly detection. Use the proposed dynamic threshold method to evaluate telemetry data. Apply the proposed method to convert linear structure data into graph data. Our model is end-to end, and needs no domain knowledge from experts. Abstract: To ensure the stable long-time operation of satellites, evaluate the satellite status, and improve satellite maintenance efficiency, we propose an anomaly detection method based on graph neural network and dynamic threshold (GNN-DTAN). Firstly, we build the graph neural network model for telemetry data. The graph construction module in the model extracts the relationship between features, and the spatial dependency extraction module and the temporal dependency extraction module extract the spatial and temporal dependencies of the data, respectively. The trained model is then used to predict the data, and the anomaly score between the predicted and actual values is calculated. Finally, the wavelet variance is used to analyze the data period. A dynamic threshold method based on the period time window is used to detect anomalies in the data set. Experimental results of satellite power system telemetry data show that the proposed algorithm's accuracy reaches more than 98%, with good effectiveness and robustness.