Beneyam, Berehanu (PhD)Tesfaye, Fetene2020-03-112023-11-042020-03-112023-11-042020-02http://etd.aau.edu.et/handle/123456789/21109For 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%.en-USroot cause analysistrouble tickethistory alarmlog fileBayesian networkThesis