Paper Info
Title
A distribution-based approach to anomaly detection and application to 3G mobile traffic
Abstract
In this work we present a novel scheme for statistical-based anomaly detection in 3G cellular networks. The traffic data collected by a passive monitoring system are reduced to a set of per-mobile user counters, from which time-series of unidimensional feature distributions are derived. An example of feature is the number of TCP SYN packets seen in uplink for each mobile user in fixed-length time bins. We design a changedetection algorithm to identify deviations in each distribution time-series. Our algorithm is designed specifically to cope with the marked non-stationarities, daily/weekly seasonality and longterm trend that characterize the global traffic in a real network. The proposed scheme was applied to the analysis of a large dataset from an operational 3G network. Here we present the algorithm and report on our practical experience with the analysis of real data, highlighting the key lessons learned in the perspective of the possible adoption of our anomaly detection tool on a production basis.
Year
DOI
Venue
2009
10.1109/GLOCOM.2009.5425651
GLOBECOM
Keywords
Field
DocType
3G mobile communication,cellular radio,telecommunication security,3G cellular networks,3G mobile traffic,change-detection algorithm,distribution time series,fixed-length time bins,operational 3G network,passive monitoring system,statistical-based anomaly detection,traffic data,unidimensional feature distributions,uplink
Anomaly detection,Algorithm design,Passive monitoring,Computer science,Mobile traffic,Network packet,Computer network,Real-time computing,Feature extraction,Cellular network,Telecommunications link
Conference
ISSN
Citations 
PageRank 
1930-529X
18
1.39
References 
Authors
21
4
Name
Order
Citations
PageRank
Alessandro D'Alconzo133026.01
Angelo Coluccia224133.15
Fabio Ricciato376874.83
Peter Romirer-Maierhofer416014.18