Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network Behavior

The growing complexity of cellular networks makes it harder for network operators to control and manage the system. To ease the management and automatically detect network problems, unsupervised techniques have been put to use. This work proposes a novel method that combines Multi-Resolution Analysi...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan Cantizani-Estepa, Sergio Fortes, Javier Villegas, Javier Rasines, Raul Martin Cuerdo, Raquel Barco
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10763485/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850065880598183936
author Juan Cantizani-Estepa
Sergio Fortes
Javier Villegas
Javier Rasines
Raul Martin Cuerdo
Raquel Barco
author_facet Juan Cantizani-Estepa
Sergio Fortes
Javier Villegas
Javier Rasines
Raul Martin Cuerdo
Raquel Barco
author_sort Juan Cantizani-Estepa
collection DOAJ
description The growing complexity of cellular networks makes it harder for network operators to control and manage the system. To ease the management and automatically detect network problems, unsupervised techniques have been put to use. This work proposes a novel method that combines Multi-Resolution Analysis (MRA) by wavelet transforms and unsupervised clustering with pre-initialized Gaussian Mixture Models (GMMs) for the totally unsupervised grouping of cellular network behaviors using different metrics. The application of multi-resolution decomposition, allows the much simpler clustering technique to take into account temporal information that would require of a much complex method otherwise, being useful for cluster analysis by experts as different duration issues are now segregated and automatically labeled. The generated labels are indicative of the intensity and duration of the anomalies, such labeling can be linguistic or visual, providing faster issue identification. The proposed approach has been tested with real network data, successfully separating different behaviors analyzed in the evaluation section of the manuscript.
format Article
id doaj-art-45fd20a4af074debad5c84ea82dc84d0
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-45fd20a4af074debad5c84ea82dc84d02025-08-20T02:48:54ZengIEEEIEEE Access2169-35362024-01-011217950617951510.1109/ACCESS.2024.350483010763485Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network BehaviorJuan Cantizani-Estepa0https://orcid.org/0000-0002-9337-8912Sergio Fortes1https://orcid.org/0000-0002-5857-6403Javier Villegas2https://orcid.org/0000-0002-5799-8540Javier Rasines3Raul Martin Cuerdo4Raquel Barco5https://orcid.org/0000-0002-8993-5229Telecommunication Research Institute (TELMA), E.T.S. Ingeniería de Telecomunicación, University of Málaga, Málaga, SpainTelecommunication Research Institute (TELMA), E.T.S. Ingeniería de Telecomunicación, University of Málaga, Málaga, SpainTelecommunication Research Institute (TELMA), E.T.S. Ingeniería de Telecomunicación, University of Málaga, Málaga, SpainEricsson-GAIA Sweden, Kista, SwedenEricsson-NDO SW Research and Development, Madrid, SpainTelecommunication Research Institute (TELMA), E.T.S. Ingeniería de Telecomunicación, University of Málaga, Málaga, SpainThe growing complexity of cellular networks makes it harder for network operators to control and manage the system. To ease the management and automatically detect network problems, unsupervised techniques have been put to use. This work proposes a novel method that combines Multi-Resolution Analysis (MRA) by wavelet transforms and unsupervised clustering with pre-initialized Gaussian Mixture Models (GMMs) for the totally unsupervised grouping of cellular network behaviors using different metrics. The application of multi-resolution decomposition, allows the much simpler clustering technique to take into account temporal information that would require of a much complex method otherwise, being useful for cluster analysis by experts as different duration issues are now segregated and automatically labeled. The generated labels are indicative of the intensity and duration of the anomalies, such labeling can be linguistic or visual, providing faster issue identification. The proposed approach has been tested with real network data, successfully separating different behaviors analyzed in the evaluation section of the manuscript.https://ieeexplore.ieee.org/document/10763485/Anomaly detectioncellular networksclusteringmultiresolution analysis (MRA)Gaussian mixture model (GMM)
spellingShingle Juan Cantizani-Estepa
Sergio Fortes
Javier Villegas
Javier Rasines
Raul Martin Cuerdo
Raquel Barco
Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network Behavior
IEEE Access
Anomaly detection
cellular networks
clustering
multiresolution analysis (MRA)
Gaussian mixture model (GMM)
title Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network Behavior
title_full Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network Behavior
title_fullStr Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network Behavior
title_full_unstemmed Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network Behavior
title_short Transform-Based Multiresolution Decomposition for Unsupervised Learning and Data Clustering of Cellular Network Behavior
title_sort transform based multiresolution decomposition for unsupervised learning and data clustering of cellular network behavior
topic Anomaly detection
cellular networks
clustering
multiresolution analysis (MRA)
Gaussian mixture model (GMM)
url https://ieeexplore.ieee.org/document/10763485/
work_keys_str_mv AT juancantizaniestepa transformbasedmultiresolutiondecompositionforunsupervisedlearninganddataclusteringofcellularnetworkbehavior
AT sergiofortes transformbasedmultiresolutiondecompositionforunsupervisedlearninganddataclusteringofcellularnetworkbehavior
AT javiervillegas transformbasedmultiresolutiondecompositionforunsupervisedlearninganddataclusteringofcellularnetworkbehavior
AT javierrasines transformbasedmultiresolutiondecompositionforunsupervisedlearninganddataclusteringofcellularnetworkbehavior
AT raulmartincuerdo transformbasedmultiresolutiondecompositionforunsupervisedlearninganddataclusteringofcellularnetworkbehavior
AT raquelbarco transformbasedmultiresolutiondecompositionforunsupervisedlearninganddataclusteringofcellularnetworkbehavior