Date of Award
Summer 2021
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
First Advisor
Ahamed, Iqbal S.
Abstract
The tremendous growth of mobile devices, IOT devices, applications and many other services have placed high demand on mobile and wireless network infrastructures. Much research and development of 5G mobile networks have found the way to support the huge volume of traffic, extracting of fine-gained analytics and agile management of mobile network elements, so that it can maximize the user experience. It is very challenging to accomplish the tasks as mobile networks increase the complexity, due to increases in the high volume of data penetration, devices, and applications. One of the solutions, advance machine learning techniques, can help to mitigate the large number of data and algorithm driven applications. This work mainly focus on extensive analysis of mobile traffic for improving the performance, key performance indicators and quality of service from the operations perspective. The work includes the collection of datasets and log files using different kind of tools in different network layers and implementing the machine learning techniques to analyze the datasets to predict mobile traffic activity. A wide range of algorithms were implemented to compare the analysis in order to identify the highest performance. Moreover, this thesis also discusses about network slicing architecture its use cases and how to efficiently use network slicing to meet distinct demands.