Multi-agent DRL-based Multipath Scheduling for Video Streaming with QUIC
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.07.2024 · 20 (7) · 1-23
DOI: 10.1145/3649139 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 16.05.2024. Verfasst von Xueqiang Han und 3 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hunan Young Talents, Training Program for Excellent Young Innovators of Changsha.
Abstract (Originalsprache)
The popularization of video streaming brings challenges in satisfying diverse Quality of Service (QoS) requirements. The multipath extension of the Quick UDP Internet Connection (QUIC) protocol, also called MPQUIC, has the potential to improve video streaming performance with multiple simultaneously transmitting paths. The multipath scheduler of MPQUIC determines how to distribute the packets onto different paths. However, while applying current multipath schedulers into MPQUIC, our experimental results show that they fail to adapt to various receive buffer sizes of different devices and comprehensive QoS requirements of video streaming. These problems are especially severe under heterogeneous and dynamic network environments. To tackle these problems, we propose MARS, a Multi-agent deep Reinforcement learning (MADRL)-based Multipath QUIC Scheduler, which is able to promptly adapt to dynamic network environments. It exploits the MADRL method to learn a neural network for each path and generate scheduling policy. Besides, it introduces a novel multi-objective reward function that takes out-of-order queue size and different QoS metrics into consideration to realize adaptive scheduling optimization. We implement MARS in an MPQUIC prototype and deploy in Dynamic Adaptive Streaming over HTTP system. Then, we compare it with the state-of-the-art multipath schedulers in both emulated and real-world networks. Experimental results show that MARS outperforms the other schedulers with better adaptive capability regarding the receive buffer sizes and QoS.
Förderung
- National Natural Science Foundation of China
- Hunan Young Talents
- Training Program for Excellent Young Innovators of Changsha
Zitieren
APA
Han, X., Han, B., Li, J., & Song, C. (2024). Multi-agent DRL-based Multipath Scheduling for Video Streaming with QUIC. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(7), 1-23. https://doi.org/10.1145/3649139
Vancouver
Han X, Han B, Li J, Song C. Multi-agent DRL-based Multipath Scheduling for Video Streaming with QUIC. ACM Transactions on Multimedia Computing, Communications, and Applications. 2024;20(7):1-23. doi:10.1145/3649139
BibTeX
@article{Han2024,
author = {Han, Xueqiang and Han, Biao and Li, Jinrong and Song, Congxi},
title = {Multi-agent DRL-based Multipath Scheduling for Video Streaming with QUIC},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2024},
volume = {20},
number = {7},
pages = {1--23},
doi = {10.1145/3649139}
}
EUVIMED