Root Cause Analysis of Base Station Outage using Bayesian Network for Addis Ababa
No Thumbnail Available
Date
2020-02
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
For telecom operators, base station is one of the most important mobile network
component from which messages are sent and received directly to/from users. The base
station consists of different hardware and software components. Any of these
components could experience various types of faults (critical, major and minor) that may
cause partial or full failure of the base station until correction is made. Base station outage
results in its users’ service interruption or quality degradation that in turn brings to the
operator churn of users/services and loss of revenue. Therefore, outage is needed to be
monitor and its cause should be identified timely for timely maintenance actions.
To reduce maintenance time and cost, different advanced outage root cause analysis
methods have been studied and applied. However, there are limited studies in the context
of Ethiopia. The objective of this thesis is to present root cause analysis of base station
outage for Addis Ababa using Bayesian network empowered by trouble ticket, log file,
and history alarm.
Results show that application of root causes analysis can be achieved to identify,
categorize and define appropriate supportive action for base station outage. By
analyzing, the base station outage based on collected history alarm, log file and trouble
ticket data can compute probability distribution and provide a priority checking. For
instance, the result from historical data collected for year shows that the performance
of Bayesian network with an accuracy of 94%.
Description
Keywords
root cause analysis, trouble ticket, history alarm, log file, Bayesian network