A Data Analysis Methodology for Obtaining Network Slices Towards 5G Cellular Networks

Mobile Network Operators (MNOs) are investigating new business opportunities and planning to launch new revenue generating services in the context of 5G deployments. In order to achieve this, MNOs are willing to open up new services and applications to end users as well as vertical industries such as automotive, health, entertainment in order to obtain new revenues. Thanks to recent advances in virtualization technologies, network slicing is one promising approach that can be utilized by MNOs for generating new services and applications that are tailored to demands of end users and vertical industries. Although there have been many works on network slicing applied to mobile network infrastructure, data analytic approach using real world network dataset that investigates how many network slices are needed for each MNOs is still missing. In this paper, we propose a methodology to extract the number of network slices specific to each MNOs via applying clustering on Key Parameter Indicators (KPIs) of major telecommunication operators. Our large scale data analysis results indicate that the number of network slices may differ depending on network quality of MNOs. For some MNOs up to five different network slices can be obtained which correspond to launching different services and applications on each selected network slice.