The complexity and scale of telecommunication networks have led to a growing interest in automated systems for detecting anomalies. However, there has been less focus on classifying anomalies detected on network Key Performance Indicators (KPI), resulting in a lack of information about anomaly characteristics and classification processes. To address this, this paper proposes a modular framework for classifying anomalies. The framework separates the anomaly classifier and the detector, allowing for a distinct treatment of anomaly detection and classification tasks on time series. The objectives of this study are to develop a time series simulator that generates synthetic time series resembling real-world network KPI behavior, to build a detection model for identifying anomalies in the time series, to build classification models that accurately categorize detected anomalies into predefined classes, and to evaluate the performance of the classification framework on simulated and real-world network KPI time series. The study has demonstrated the strong performance of the anomaly classification models trained on simulated anomalies when applied to real-world network time series data.
Anomaly Classification in Telecommunication Network KPI Time Series
