Anomaly detection algorithms for the sleeping cell detection in LTE networks

Sergey Chernov, Michael Cochez, Tapani Ristaniemi

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

The Sleeping Cell problem is a particular type of cell degradation in Long-Term Evolution (LTE) networks. In practice such cell outage leads to the lack of network service and sometimes it can be revealed only after multiple user complains by an operator. In this study a cell becomes sleeping because of a Random Access Channel (RACH) failure, which may happen due to software or hardware problems. For the detection of malfunctioning cells, we introduce a data mining based framework. In its core is the analysis of event sequences reported by a User Equipment (UE) to a serving Base Station (BS). The crucial element of the developed framework is an anomaly detection algorithm. We compare performances of distance, centroid distance and probabilistic based methods, using Receiver Operating Characteristic (ROC) and Precision-Recall curves. Moreover, the theoretical comparison of the methods' computational efficiencies is provided. The sleeping cell detection framework is verified by means of a dynamic LTE system simulator, using Minimization of Drive Testing (MDT) functionality. It is shown that the sleeping cell can be pinpointed.

Original languageEnglish
Title of host publication2015 IEEE 81st Vehicular Technology Conference, VTC Spring 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479980888
DOIs
Publication statusPublished - 1 Jul 2015
Externally publishedYes
Event81st IEEE Vehicular Technology Conference, VTC Spring 2015 - Glasgow, United Kingdom
Duration: 11 May 201514 May 2015

Publication series

NameIEEE Vehicular Technology Conference
Volume2015
ISSN (Print)1550-2252

Conference

Conference81st IEEE Vehicular Technology Conference, VTC Spring 2015
CountryUnited Kingdom
CityGlasgow
Period11/05/1514/05/15

Fingerprint

Dive into the research topics of 'Anomaly detection algorithms for the sleeping cell detection in LTE networks'. Together they form a unique fingerprint.

Cite this