Network Exceptions Modelling Using Hidden Markov Model: A Case Study of Ericsson’s DroppedCall Data
Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
In telecommunication, the series of mobile network exceptions is a processwhich exhibits surges and bursts. The bursty part is usually caused by systemmalfunction. Additionally, the mobile network exceptions are often timedependent. A model that successfully captures these aspects will make troubleshootingmuch easier for system engineers. The Hidden Markov Model(HMM) is a good candidate as it provides a mechanism to capture both thetime dependency and the random occurrence of bursts. This thesis focuses onan application of the HMM to mobile network exceptions, with a case study ofEricsson’s Dropped Call data. For estimation purposes, two methods of maximumlikelihood estimation for HMM, namely, EM algorithm and stochasticEM algorithm, are used.
Place, publisher, year, edition, pages
2014. , 43 p.
Hidden Markov Model, Mobile Network, Stochastic EM algorithm
Probability Theory and Statistics
IdentifiersURN: urn:nbn:se:uu:diva-251382OAI: oai:DiVA.org:uu-251382DiVA: diva2:805925
Subject / course
Master Programme in Statistics
2014-06-02, Ekonomikum, Kyrkogårdsgatan 10, Uppsala, 09:16 (English)
Ahmad, Rauf, Senior lecturerSchüller, Henrik
Wallentin, Fan Yang