Machine Learning Approaches to Early Fault Detection and Identification in NFV Architectures
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 200-208
Abstract
Virtualization technologies become pervasive in networking, as a way to better exploit hardware capabilities and to quickly deploy tailored networking solutions for customers. But these new programmability abilities of networks also come with new management challenges: it is critical to quickly detect performance degradation, before they impact Quality of Service (QoS) or produce outages and alarms, as this takes part in the closed loop that adapts resources to services. This paper addresses the early detection, localization and identification of faults, before alarms are produced. We rely on the abundance of metrics available on virtualized networks, and explore various data preprocessing and classification techniques. As all Machine Learning approaches must be fed with large datasets, we turn to our advantage the softwarization of networks: one can easily deploy in a cloud the very same software that is used in production, and analyze its behaviour under stress, by fault injection.Keywords
This publication has 10 references indexed in Scilit:
- Localizing Faults in Cloud Systems2018
- Anomaly detection for openstack services with process-related topological analysis2017
- A Fault Correlation Approach to Detect Performance Anomalies in Virtual Network Function Chains2017
- Stimulus-based sandbox for learning resource dependencies in virtualized distributed applications2017
- Towards Black-Box Anomaly Detection in Virtual Network Functions2016
- XGBoost2016
- Failure Diagnosis for Distributed Systems using Targeted Fault InjectionIEEE Transactions on Parallel and Distributed Systems, 2016
- Automatic Fault Diagnosis in Cloud Infrastructure2013
- CloudPD: Problem determination and diagnosis in shared dynamic clouds2013
- Towards highly reliable enterprise network services via inference of multi-level dependencies2007