CellPAD: Detecting Performance Anomalies in Cellular Networks via Regression Analysis

Abstract

How to accurately detect Key Performance Indicator (KPI) anomalies is a critical issue in cellular network management. We present CellPAD, a unified performance anomaly detection framework for KPI time-series data. CellPAD realizes simple statistical modeling and machine-learning-based regression for anomaly detection; in particular, it specifically takes into account seasonality and trend components as well as supports automated prediction model retraining based on prior detection results. We demonstrate how CellPAD detects two types of anomalies of practical interest, namely sudden drops and correlation changes, based on a large-scale real-world KPI dataset collected from a metropolitan LTE network. We explore various prediction algorithms and feature selection strategies, and provide insights into how regression analysis can make automated and accurate KPI anomaly detection viable.