Digital Library

cab1

 
Title:      APPLICATION OF MARKOV CHAIN TO PREDICT FAULTS FROM REAL TIME ALARM DATA
Author(s):      Ahmad Kazmi
ISBN:      978-972-8939-19-9
Editors:      Hans Weghorn, Jörg Roth and Pedro Isaías
Year:      2010
Edition:      Single
Keywords:      Alarm prediction, Faults prediction, Telecommunication system, Markov Chain
Type:      Short Paper
First Page:      197
Last Page:      201
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      Current telecommunication systems are complex heterogeneous networks with parts from various vendors. Obviously such complex systems will face a number of faults that may deny services to the end users, hence resulting in revenue losses to the telecommunication companies. Various techniques are proposed that predict fault based on historical alarm data. One such technique is from the Telecom Alarm Sequence Analyzer (TASA) project that has proposed to classify the sequence of alarms into 3 categories. We have used TASA techniques to categorize alarms and then Markov Chain technique for classification of future sequence of alarms according to one of TASA categories. Once we know the category of a sequence of alarms we can predict the alarm (fault) itself. We have applied our proposed method on real time alarm data of a telecommunication company. Furthermore, we present the alarm prediction results to verify that our approach has merit.
   

Social Media Links

Search

Login