Unit:
Κατεύθυνση Δικτύωση ΥπολογιστώνΠληροφορική
Author:
Thanopoulos Alexandros-Ioannis
Supervisors info:
Αλωνιστιώτη Αθανασία, Αναπληρώτρια Καθηγήτρια, Τμήμα Πληροφορικής και Τηλεπικοινωνιών, Εθνικό και Καποδιστριακό Πανεπιστήμιο Αθηνών.
Σταυρακάκης Ιωάννης, Καθηγητής, Τμήμα Πληροφορικής και Τηλεπικοινωνιών, Εθνικό και Καποδιστριακό Πανεπιστήμιο Αθηνών.
Αλεξανδρόπουλος Γεώργιος, Αναπληρωτής Καθηγητής, Τμήμα Πληροφορικής και Τηλεπικοινωνιών, Εθνικό και Καποδιστριακό Πανεπιστήμιο Αθηνών.
Original Title:
Quality of Service Prediction in 5G and Beyond Networks
Translated title:
Quality of Service Prediction in 5G and Beyond Networks
Summary:
Determining whether the network can provide the required resources - and as a result the required Quality of Service (QoS) - for Connected and Automated Mobility (CAM) applications is crucial, as human safety is involved. In order to identify potential QoS deterioration events in a timely manner, Machine Learning - which is currently considered a momentous enabler for the 5G and beyond systems -, can be exploited in order to timely predict such changes in the QoS and proactively notify the CAM application in order for it to flexibly adapt. This thesis summarizes the outputs of Quality of Service Prediction in 5G and Beyond Networks. Initially, it provides a presentation of the state-of-the-art on the QoS prediction topic for wireless networks, while it also introduces the Tele-operated Driving (ToD) CAM Use Case (UC) and its requirements for timely predicting QoS Key Performance Indicators (KPIs). Next, it discusses the concept of Deep Learning, focusing on its application for QoS prediction use cases; an overview of Deep Neural Networks (DNNs) is provided, as well as insights on Multivariate Multistep Time Series Prediction using Long-Short Term Memory (LSTM) architectures. Most importantly, it comprises a comprehensive description of a QoS prediction solution and architecture, data model and methodology. An extended description of the evaluation environment is then provided. A comprehensive list of evaluation scenarios based on the ToD use case are presented, along with related discussions and conclusions on the presented results.
Main subject category:
Technology - Computer science
Keywords:
B5G, mobile networks, QoS, ToD
File:
File access is restricted only to the intranet of UoA.
thesis_en3180002.pdf
3 MB
File access is restricted only to the intranet of UoA.
