Traffic Pattern Modelling for 5G Base Stations

Erik Bengtsson () and Linnea Larsson ()

Description

This thesis is about the network traffic to and from Ericsson's 5G base stations. The work involves investigating whether it is possible to train an AI model that can predict what the data traffic from mobile devices looks like at different times at a certain base station, and further to train different models and compare and evaluate them. The aim is to gain knowledge about the times the traffic is lower in order to then allow certain components to go into sleep mode and, hence, to reduce energy consumption.