Abstract
5G mobile networks are expected to provide services that require low latency, high data rate, and massive connectivity. In this context, being able to analyze and possibly predict the performance experienced by end users (e.g., in terms of latency, throughput, and connection reliability) is essential for traffic management and network optimization. By leveraging measurements performed on real networks, this thesis work will focus on the development and testing of techniques for reliable prediction of network/user performance, potentially applying machine and deep learning techniques.
Keywords
5G system
machine learning
Performance
ERC sector(s)
PE Physical Sciences and Engineering
Name supervisor
Giuseppe Caso
E-mail
giuseppe.caso@kau.se
Name of Department/Faculty/School
Department of Mathematics and Computer Science
Name of the host University
Karlstad University (KAU)
EUNICE partner e-mail of destination Research
james.lees@kau.se
Country
Sweden
Thesis level
Master
Minimal language knowledge requisite
English B1
English B2
Thesis mode
Hybrid
Start date
Call deadline
Length of the research internship
6 months
Financial support available (other than E+)
Maybe