Document Type

Theses, Ph.D

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

Electrical and electronic engineering

Publication Details

A thesis submitted in partial fulfilment of the requirements for the award of the degree of Doctor of Philosophy, Technological University Dublin, January 2023.

Abstract

Video streaming over the Internet requires an optimized delivery system given the advances in network architecture, for example, Software Defined Networks. Machine Learning (ML) models have been deployed in an attempt to predict the quality of the video streams. Some of these efforts have considered the prediction of Quality of Delivery (QoD) metrics of the video stream in an effort to measure the quality of the video stream from the network perspective. In most cases, these models have either treated the ML algorithms as black-boxes or failed to capture the network dynamics of the associated video streams.

This PhD investigates the effects of network dynamics in QoD prediction using ML techniques. The hypothesis that this thesis investigates is that ML techniques that model the underlying network dynamics achieve accurate QoD and video quality predictions and measurements. The thesis results demonstrate that the proposed techniques offer performance gains over approaches that fail to consider network dynamics. This thesis results highlight that adopting the correct model by modelling the dynamics of the network infrastructure is crucial to the accuracy of the ML predictions. These results are significant as they demonstrate that improved performance is achieved at no additional computational or storage cost. These techniques can help the network manager, data center operatives and video service providers take proactive and corrective actions for improved network efficiency and effectiveness.

DOI

https://doi.org/10.21427/NMH6-S029

Funder

Science Foundation Ireland

Download
Contact the Author


Share

COinS