Active Rule Mining for Multivariate Anomaly Detection in Radio Access Networks
It addresses the need for interpretable anomaly detection in radio access networks, enabling operators to understand root causes and take remedial actions, but is incremental as it builds on existing explainable AI methods.
The paper tackles the problem of explaining anomalies detected by multivariate anomaly detectors in radio access networks, proposing a semi-autonomous rule miner that generates actionable rules for network operators, demonstrated with time series data.
Multivariate anomaly detection finds its importance in diverse applications. Despite the existence of many detectors to solve this problem, one cannot simply define why an obtained anomaly inferred by the detector is anomalous. This reasoning is required for network operators to understand the root cause of the anomaly and the remedial action that should be taken to counteract its occurrence. Existing solutions in explainable AI may give cues to features that influence an anomaly, but they do not formulate generalizable rules that can be assessed by a domain expert. Furthermore, not all outliers are anomalous in a business sense. There is an unfulfilled need for a system that can interpret anomalies predicted by a multivariate anomaly detector and map these patterns to actionable rules. This paper aims to fulfill this need by proposing a semi-autonomous anomaly rule miner. The proposed method is applicable to both discrete and time series data and is tailored for radio access network (RAN) anomaly detection use cases. The proposed method is demonstrated in this paper with time series RAN data.