Ensemble2: Anomaly Detection via EVT-Ensemble Framework for Seasonal KPIs in Communication Network
This addresses the need for automated anomaly detection in network management systems, but it appears incremental as it builds on existing ensemble and threshold adjustment methods.
The paper tackles the problem of anomaly detection for seasonal KPIs in communication networks by proposing the Ensemble2 framework, which uses ensemble learning and automatically adjusts thresholds based on extreme value theory, achieving a speed of ~10 pts/s on an Intel i5 platform.
KPI anomaly detection is one important function of network management system. Traditional methods either require prior knowledge or manually set thresholds. To overcome these shortcomings, we propose the Ensemble2 framework, which applies ensemble learning to improve exogenous capabilities. Meanwhile, automatically adjusts thresholds based on extreme value theory. The model is tested on production datasets to verify its effectiveness. We further optimize the model using online learning, and finally running at a speed of ~10 pts/s on an Intel i5 platform.