IMDEA Networks Institute Publications Repository

A Novel Methodology for the Automated Detection and Classification of Networking Anomalies

Moulay, Mohamed and García, Rafael and Mancuso, Vincenzo and Fernández Anta, Antonio and Rojo, Pablo and Lazaro, Javier (2020) A Novel Methodology for the Automated Detection and Classification of Networking Anomalies. In: INFOCOM 2020 Workshop on Network Intelligence (NI 2020): Learning and Optimizing Future Networks, 6-9 July 2020, Toronto.

[img] PDF - Accepted Version
Download (377Kb)

Abstract

The active growth and dynamic nature of cellular networks makes challenging accommodating end-users with flawless quality of service. Identification of network problems leveraging on machine learning has gained a lot of visibility in the past few years, resulting in dramatically improved cellular network services. In this paper, we present a novel methodology to automate the fault identification process in a cellular network and to classify network anomalies, which combines supervised and unsupervised machine learning algorithms. Our experiments using real data from operational commercial mobile networks show that our method can automatically identify and classify networking anomalies, so to enable timely and precise troubleshooting actions.

Item Type: Conference or Workshop Papers (Paper)
Subjects: UNSPECIFIED
Divisions: UNSPECIFIED
Depositing User: Mohamed Lamine
Date Deposited: 13 Apr 2020 08:34
Last Modified: 13 Apr 2020 08:34
URI: http://eprints.networks.imdea.org/id/eprint/2126

Actions (login required)

View Item View Item