QoE estimation-based server benchmarking for virtual video delivery platform

Lauri Koskimies, Tarik Taleb, Miloud Bagaa

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    7 Citations (Scopus)
    220 Downloads (Pure)

    Abstract

    This paper introduces a Quality of Experience (QoE) estimation-based server benchmarking system, which can be utilized as a part of QoE-optimized resource provisioning in our envisioned virtual video delivery platform. The system has been targeted for benchmarking virtual video streaming servers, i.e., virtual server flavors deployed in a cloud environment, based on resulting QoE estimates. The paper also presents another layer to the benchmarking by showing how to optimize stream segment duration in terms of estimated QoE. The QoE estimation in the system is based on a Pseudo-Subjective Quality Assessment (PSQA) method developed for video streaming. Output of the system, i.e., QoE estimation-based benchmarks, helps to find out how different factors can affect video streaming QoE which in turn makes parameter and resource optimizations possible. Moreover, the paper presents experimental benchmarking results obtained in a cloud environment.
    Original languageEnglish
    Title of host publication2017 IEEE International Conference on Communications (ICC)
    PublisherIEEE
    Number of pages6
    ISBN (Electronic)978-1-4673-8999-0
    ISBN (Print)978-1-4673-9000-2
    DOIs
    Publication statusPublished - May 2017
    MoE publication typeA4 Conference publication
    EventIEEE International Conference on Communications - Paris, France
    Duration: 21 May 201725 May 2017

    Publication series

    Name IEEE International Conference on Communications (ICC)
    PublisherIEEE
    ISSN (Electronic)1938-1883

    Conference

    ConferenceIEEE International Conference on Communications
    Abbreviated titleICC
    Country/TerritoryFrance
    CityParis
    Period21/05/201725/05/2017

    Fingerprint

    Dive into the research topics of 'QoE estimation-based server benchmarking for virtual video delivery platform'. Together they form a unique fingerprint.

    Cite this