Toward Optimal Live Video Streaming QoE: A Deep Feature-Fusion Approach
IEEE/ACM Transactions on Networking · 2024-06 · 32 (3) · 2360-2375
DOI: 10.1109/tnet.2024.3351832 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE/ACM Transactions on Networking, 2024-06. Verfasst von Huanhuan Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Innovation Research Group Project of NSFC, NSFC Project, China National Post-Doctoral Program for Innovative Talents.
Abstract (Originalsprache)
Maximizing the quality of experience (QoE) for live video streaming is a long-standing challenge. Traditional video transport protocols, represented by a few deterministic rules, can hardly adapt to the highly heterogeneous and dynamic modern Internet environments. Emerging learning-based algorithms have demonstrated the potential to meet above challenge. However, our measurement study reveals an alarming long-tail performance issue: these learning-based algorithms tend to be bottlenecked by occasional catastrophic events due to the built-in exploration mechanisms. In this work, we propose Loki-plus, which improves the robustness of learning-based model by coherently integrating it with a rule-based algorithm. To enable integration at deep feature level, we first reverse-engineer the rule-based algorithm into an equivalent “black-box” neural network, and then devise a transformer-based continual learning model with effective historical feature reservation. Then, we design a network feature-aware fusion mechanism to fuse the two models in a deep manner. We train Loki-plus in a full-fledged live video system through online learning, and evaluate it over massive video sessions, in comparison to state-of-the-art rule-based and learning-based solutions. The results show that Loki-plus improves not only the average but also the tail performance substantially.
Förderung
- Innovation Research Group Project of NSFC
- NSFC Project
- China National Post-Doctoral Program for Innovative Talents
- China Post-Doctoral Science Foundation
- Youth Top Talent Support Program
Zitieren
APA
Zhang, H., Zhou, A., Wang, G., Li, C., & Ma, H. (2024). Toward Optimal Live Video Streaming QoE: A Deep Feature-Fusion Approach. IEEE/ACM Transactions on Networking, 32(3), 2360-2375. https://doi.org/10.1109/tnet.2024.3351832
Vancouver
Zhang H, Zhou A, Wang G, Li C, Ma H. Toward Optimal Live Video Streaming QoE: A Deep Feature-Fusion Approach. IEEE/ACM Transactions on Networking. 2024;32(3):2360-2375. doi:10.1109/tnet.2024.3351832
BibTeX
@article{Zhang2024,
author = {Zhang, Huanhuan and Zhou, Anfu and Wang, Guangping and Li, Chaoyue and Ma, Huadong},
title = {Toward Optimal Live Video Streaming QoE: A Deep Feature-Fusion Approach},
journal = {IEEE/ACM Transactions on Networking},
year = {2024},
volume = {32},
number = {3},
pages = {2360--2375},
doi = {10.1109/tnet.2024.3351832}
}
EUVIMED