Introducing an Unsupervised Automated Solution for Root Cause Diagnosis in Mobile Networks - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Network and Service Management Year : 2019

Introducing an Unsupervised Automated Solution for Root Cause Diagnosis in Mobile Networks

(1, 2) , (3, 1, 4) , (1) , (5)
1
2
3
4
5

Abstract

Today's network operators strive to create self-healing cellular networks that have a fully automated troubleshooting management process. To this end, the network monitoring system should be capable of detecting issues, diagnosing them, and triggering the adequate recovery action. In this paper, we propose an unsupervised solution to diagnose the root causes of network issues. As monitoring systems collect a large number of logs from the different devices in their networks, it is possible to determine which connections resulted in a poor user experience and apply a failed/successful label. Our solution, Automatic Root Cause Diagnosis (ARCD), analyzes labeled connection logs to identify the major contributors to the network inefficiency (e.g., a faulty core device) as well as the incompatibilities between different elements (e.g., make and model of a phone not being able to access a service). We evaluate the effectiveness of our solution by using logs from three different real cellular networks. In each case, ARCD was able to identify the major contributors and the most widespread incompatibilities. In the three cases, the precision (detection accuracy) and the recall (detection rate) are higher than 90%.
Fichier principal
Vignette du fichier
main(8).pdf (392.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02377865 , version 1 (24-11-2019)

Identifiers

Cite

Maha Mdini, Gwendal Simon, Alberto Blanc, Julien Lecoeuvre. Introducing an Unsupervised Automated Solution for Root Cause Diagnosis in Mobile Networks. IEEE Transactions on Network and Service Management, 2019, pp.1-1. ⟨10.1109/TNSM.2019.2954340⟩. ⟨hal-02377865⟩
73 View
275 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More