Investigation of Mobile Network Traffic Using Hadoop and Mahout Machine Learning Methods

Since the emergence of mobile networks, the number of mobile subscriptions has continued to increase year after year. To efficiently assign wireless resources such as spectrum (which is rare and expensive), the network operator needs to process and analyze information and statistics about each base station and the traffic that passes through it. This thesis focuses on processing and analyzing two datasets provided by our industrial partner, Ericsson, Canada. A detailed approach that uses Apache Hadoop and the Mahout machine learning library to process and analyze the datasets is presented. The analysis provides insights to the network operator about the resource usage of network devices. This information is of great importance to network operators for efficient and effective management of resources and user experience. Furthermore, an investigation has been conducted that evaluates the impact of executing the Mahout clustering algorithms with various system and workload parameters on a Hadoop cluster.