Graph neural network approach for anomaly detection

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.