Applying Machine Learning to Service Assurance in Network Function Virtualization Environment

Abstract

With the complexity, heterogeneity, and scale of today's networks, service assurance is becoming increasingly complicated. Meanwhile, significant amounts of telemetry data are collected on virtual network functions; it has been proposed that machine learning can be used to predict/forecast key performance indicators by analyzing this data and then taking actions to prevent severe service degradation. In this paper, we demonstrate the process of telemetry data collecting and filtering, feature dimension reduction, and machine learning algorithm selection for detecting packet loss in a NFV based vEPC test system.