Title: Quality of experience prediction model for video streaming in SDN networks

Authors: Tasnim Abar; Asma Ben Letaifa; Sadok El Asmi

Addresses: COSIM Research Lab, MEDIATRON Lab, Higher School of Communications of Tunis (SUP'COM), University of Carthage, El Ghazala, 2083 Ariana, Tunis, Tunisia ' COSIM Research Lab, MEDIATRON Lab, Higher School of Communications of Tunis (SUP'COM), University of Carthage, El Ghazala, 2083 Ariana, Tunis, Tunisia ' COSIM Research Lab, MEDIATRON Lab, Higher School of Communications of Tunis (SUP'COM), University of Carthage, El Ghazala, 2083 Ariana, Tunis, Tunisia

Abstract: To evaluate the network performance, network operators rely on quality of service. This measure has shown limits and great deal of effort has been put into putting in place a new metric that more accurately reflects the quality of service offered. This measure is known as Quality of Experience (QoE). QoE reflects the user's satisfaction for a service. Today, evaluating the QoE has become paramount for service providers and content providers. This necessity pushed us to innovate and design new methods to estimate the QoE. This paper comprises two parts: the first part defines our subjective method which evaluates the video quality over SDN networks. In the second part we try to cover the impairments of subjective methods by a novel method that predicts the QoE (MOS) based on machine learning, so we employ ML-classifiers, then we calculate the performance metrics to measure the performance of each algorithm to deduce the best algorithm.

Keywords: SDN; QoS; QoE; video quality; subjective evaluation; machine learning; MOS; performance metrics; network operators; SDN controller.

DOI: 10.1504/IJWMC.2020.104769

International Journal of Wireless and Mobile Computing, 2020 Vol.18 No.1, pp.59 - 70

Accepted: 28 Jun 2019
Published online: 30 Jan 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article