Publication: DoFP+: An HTTP/3-Based Adaptive Bitrate...
Master data
Title: | DoFP+: An HTTP/3-Based Adaptive Bitrate Approach Using Retransmission Techniques |
Subtitle: | |
Abstract: | HTTP Adaptive Streaming (HAS) solutions use various adaptive bitrate (ABR) algorithms to select suitable video qualities with the objective of coping with the variations of network connections. HTTP has been evolving with various versions and provides more and more features. Most of the existing ABR algorithms do not significantly benefit from the HTTP development when they are merely supported by the most recent HTTP version. An open research question is “How can new features of the recent HTTP versions be used to enhance the performance of HAS?” To address this question, in this paper, we introduce Days of Future Past+ (DoFP+ for short), a heuristic algorithm that takes advantage of the features of the latest HTTP version, HTTP/3, to provide high Quality of Experience (QoE) to the viewers. DoFP+ leverages HTTP/3 features, including (i) stream multiplexing, (ii) stream priority, and (iii) request cancellation to upgrade low-quality segments in the player buffer while downloading the next segment. The qualities of those segments are selected based on an objective function and throughput constraints. The objective function takes into account two factors, namely the (i) average bitrate and the (ii) video instability of the considered set of segments. We also examine different strategies of download order for those segments to optimize the QoE in limited resources scenarios. The experimental results show an improvement in QoE by up to 33% while the number of stalls and stall duration for DoFP+ are reduced by 86% and 92%, respectively, compared to state-of-the-art ABR schemes. In addition, DoFP+ saves, on average, up to 16% downloaded data across all test videos. Also, we find that downloading segments sequentially brings more benefits for retransmissions than concurrent downloads; and lower-quality segments should be upgraded before other segments to gain more QoE improvement. Our source code has been published for reproducibility at https://github.com/cd-athena/DoFP-Plus. |
Keywords: | HTTP/3, ABR algorithm, QoE, HAS, DASH |
Publication type: | Article in journal (Authorship) |
Publication date: | 14.10.2022 (Online) |
Published by: |
IEEE Access
IEEE Access
(
IEEE;
)
to publication |
Title of the series: | - |
Volume number: | 10 |
Issue: | - |
First publication: | Yes |
Version: | - |
Page: | pp. 109565 - 109579 |
Versionen
Keine Version vorhanden |
Publication date: | 10.2022 |
ISBN: | - |
ISSN: | - |
Homepage: | https://ieeexplore.ieee.org/document/9919844 |
Publication date: | 14.10.2022 |
ISBN (e-book): | - |
eISSN: | 2169-3536 |
DOI: | http://dx.doi.org/10.1109/access.2022.3214827 |
Homepage: | https://ieeexplore.ieee.org/document/9919844 |
Open access |
|
Authors
Minh Nguyen (internal) |
Daniele Lorenzi (internal) |
Farzad Tashtarian (internal) |
Hermann Hellwagner (internal) |
Christian Timmerer (internal) |
Assignment
Organisation | Address | ||||
---|---|---|---|---|---|
Fakultät für Technische Wissenschaften
Institut für Informationstechnologie
|
AT - 9020 Klagenfurt am Wörthersee |
Categorisation
Subject areas | |
Research Cluster | No research Research Cluster selected |
Citation index |
Information about the citation index: Master Journal List
|
Peer reviewed |
|
Publication focus |
Classification raster of the assigned organisational units:
|
working groups |
|
Cooperations
Research activities
Projects: |
|
Publications: | No related publications |
Events: | No related events |
Lectures: | No related lectures |