Umts Network Coverage Hole Detection Using Decision Tree Classifier Machine Learning Approach

Due to various innovative mobile services and applications, traffic is constantly increasingrnin size and complexity globally and as well as locally in Ethiopia. To fulfill thesernrequirements in both quality and quantity, a wide range of radio frequency signal coveragernareas are required. One means of satisfying this requirement is proper planning andrndevising proper network management during operational phase for network coveragernhole detection for optimization of uncovered area. Measurement collection is a primaryrnstep towards analyzing and optimizing the performance of a telecommunication service.rnIn this sense, this work aims to present a solution that contributes to reduce costs andrntime in network monitoring by exploiting user equipment Measurement Report (MR)rndata via the Minimization of Drive Tests (MDT) functionality.rnAn automatic coverage hole detection based on classification techniques, which is arnDecision Tree (DT) classifier-based approach is used for rule induction to identifyrndifferent scenarios of coverage holes and their respective areas for better service deliveryrnpurposes. The main idea is to jointly observe signal strength and signal quality forrneffective coverage-hole detection. It uses a new approach to classify four coveragernscenarios such as “good coverage and good quality”, “good coverage but poor quality”,rn“poor coverage but good quality”, and “poor coverage and poor quality” in UniversalrnMobile Telecommunications System (UMTS) network considering the last three coveragernclasses as coverage -hole with different severity levels.rnThe result showed that the applied model accuracy was 99.98%, and also the proposedrnapproach could classify the target classes and allows the visualization of networkrnperformance in terms of signal strength and quality associated with a location. Allrnfour coverage scenarios were visibly observed and the results are almost uniform withrnvalidation results found from the driving test (with about 7dB and 1dB difference ofrnRSCP and Ec/No respectively considering the cumulative distribution function valuernof 18%). 77% of coverage areas were classified as good coverage condition.

Get Full Work

Report copyright infringement or plagiarism