EVoKE: summary

Title:Eledia Vodafone Kpi Evaluator
Start Date: 2011
Join Date: 2011
Status:Project is still active
Sector2G/3G/4G Mobile Network, Anomaly Detection, Pattern Recognition
PlatformWindows, .NET C# 4.0, SQL
Employer:University of Trento, DISI, ELEDIA
Position:Design and Implementation
Abstract: EVoKE (Eledia Vodafone Kpi Evaluator) is a full scale anomaly detection system for 2G, 3G, 4G cellular networks. It includes many statistical detectors (Multipass Modified three-sigma, MAD, Median Rule, BoxPlot) and a WAVELET based pattern matching detector for complex anomalies. Many filters have been included in order to improve detected alarms performance (e.g. false-positive rate) and in order to enable advanced data-mining and inference based methodologies. Moreover some filters have been specifically designed for Vodafone needs. Thanks to design and optimized algorithms, EVoKE is able to evaluate more than 30.000 cells (daily analysis) in 16 seconds. It has been tested during 2012 by Vodafone Omnitel N.V.
Tags:cellular, anomaly detection, pattern recognition, thesis

EVoKE: resources

Filetype: PDF Thesis.Presentation.Alessandro.Polo.ENG.TLC.EVoKE.pdf 1.6 Mb 2012-11-08 19:06
Filetype: PNG logo.evoke.png 4.7 Kb 2012-11-26 21:51
Ph.D. trip

Printer friendly