Graphormer-Based Bayesian Network Conditional Normalizing Flow for Multivariate Time Series Anomaly Detection in Communication Networks

High-dimensional time series data are becoming more widespread in many domains, including large-scale wireless networks for communication. However, because of its high dimensionality, label scarcity, and complicated temporal connections, anomaly detection in such data is difficult. This work proposes a Bayesian network conditional normalizing flow model for multivariate time series anomaly detection, called Graphormer-based Bayesian Network Conditional Normalizing Flow (GBNCNF), based on a graph Transformer (Graphormer) to convert the spatial and temporal dependencies of high-dimensional time series into simple evaluable conditional densities. It models the causal links between numerous time series using a Bayesian network, and it obtains representations of the interdependencies between different time series by combining LSTM modules with Graphormer modules. These representations are introduced as conditional information into the normalizing flow for density estimation, and data corresponding to low density are judged as anomalies. Experiments are conducted on two real datasets and show that our method detects anomalies more accurately than baseline methods, accurately captures the correlations between sensors, and allows users to infer the root causes of detected anomalies.