Predictive Analysis in Network Function Virtualization

Recent deployments of Network Function Virtualization (NFV) architectures have gained tremendous traction. While virtualization introduces benefits such as lower costs and easier deployment of network functions, it adds additional layers that reduce transparency into faults at lower layers. To improve fault analysis and prediction for virtualized network functions (VNF), we envision a runtime predictive analysis system that runs in parallel with existing reactive monitoring systems to provide network operators timely warnings against faulty conditions. In this paper, we propose a deep learning based approach to reliably identify anomaly events from NFV system logs, and perform an empirical study using 18 consecutive months in 2016--2018 of real-world deployment data on virtualized provider edge routers. Our deep learning models, combined with customization and adaptation mechanisms, can successfully identify anomalous conditions that correlate with network trouble tickets. Analyzing these anomalies can help operators to optimize trouble ticket generation and processing rules in order to enable fast, or even proactive actions against faulty conditions.