SLVS: A Self-Learning Approach to Achieve Near-Second Low-Latency Video Streaming Under Highly Variable Networks

doi:10.1109/TMC.2025.3528635

	SLVS: A Self-Learning Approach to Achieve Near-Second Low-Latency Video Streaming Under Highly Variable Networks
	Zhang, Guanghui 1; Liu, Ke 2,3; Xiao, Mengbai 1; Wang, Bingshu 4; Yu, Dongxiao 1; Cheng, Xiuzhen 1
	2025-06-01
发表期刊	IEEE TRANSACTIONS ON MOBILE COMPUTING
ISSN	1536-1233
卷号	24 期号:6 页码:5189-5201
摘要	Fueled by the rapid advances in high-speed mobile networks, live video streaming has seen explosive growth in recent years and some DASH-based algorithms were specifically proposed for low-latency video delivery. We conducted a measurement study for the state-of-the-art algorithms with large-scale network traces. It reveals that these algorithms are susceptible to network condition changes due to the use of solo universal adaptation logics, resulting in the playback latency that has substantial variations across highly fluctuating networks. To tackle this challenge, this paper proposes Stateful Live Video Streaming (SLVS), which is a novel self-learning approach that learns the various network features and optimizes the adaptation logic separately for different network conditions, then dynamically tunes the logic at runtime, so that bitrate decision can better match the changing networks. Moreover, we further generalize SLVS to complement the streaming platform already in service to make it compatible with any live streaming services. Extensive evaluations based on real system prototypes show that SLVS can control playback latency down to 1 s while improving Quality-of-Experience (QoE) by 17.7% to 31.8%. Moreover, it has strong robustness to maintain near-second latency over highly fluctuating networks as well as long periods of video viewing.
关键词	Streaming media Bit rate Logic Throughput Low latency communication Heuristic algorithms Bandwidth Video recording Quality assessment TCP Live video streaming adaptive streaming Quality-of-Experience (QoE)
DOI	10.1109/TMC.2025.3528635
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62302268] ; National Natural Science Foundation of China[62072439] ; National Natural Science Foundation of China[62090020] ; National Key Research and Development Plan of China[2022YFB4500400] ; Natural Science Foundation of Shandong Province[2023HWYQ-045] ; Natural Science Foundation of Shandong Province[ZR2023QF060] ; Natural Science Foundation of Shandong Province[ZR2022ZD02] ; Qingdao Natural Science Foundation[23-2-1-127-zyyd-jch] ; Taishan Scholar Project of Shandong Province[tsqn202312051]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Telecommunications
WOS记录号	WOS:001483850200031
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40649
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yu, Dongxiao
作者单位	1.Shandong Univ, Sch Comp Sci & Technol, Qingdao 266237, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100045, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 4.Northwestern Polytech Univ, Sch Software, Taicang Campus, Suzhou 215400, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Guanghui,Liu, Ke,Xiao, Mengbai,et al. SLVS: A Self-Learning Approach to Achieve Near-Second Low-Latency Video Streaming Under Highly Variable Networks[J]. IEEE TRANSACTIONS ON MOBILE COMPUTING,2025,24(6):5189-5201.
APA	Zhang, Guanghui,Liu, Ke,Xiao, Mengbai,Wang, Bingshu,Yu, Dongxiao,&Cheng, Xiuzhen.(2025).SLVS: A Self-Learning Approach to Achieve Near-Second Low-Latency Video Streaming Under Highly Variable Networks.IEEE TRANSACTIONS ON MOBILE COMPUTING,24(6),5189-5201.
MLA	Zhang, Guanghui,et al."SLVS: A Self-Learning Approach to Achieve Near-Second Low-Latency Video Streaming Under Highly Variable Networks".IEEE TRANSACTIONS ON MOBILE COMPUTING 24.6(2025):5189-5201.