Xatu: Richer Neural Network Based Prediction for Video Streaming

Author:

Nam Yun Seong1,Gao Jianfei2,Bothra Chandan2,Ghabashneh Ehab2,Rao Sanjay2,Ribeiro Bruno2,Zhan Jibin3,Zhang Hui3

Affiliation:

1. Purdue University & Google, West Lafayette, IN, USA

2. Purdue University, West Lafayette, IN, USA

3. Conviva, San Mateo, CA, USA

Abstract

The performance of Adaptive Bitrate (ABR) algorithms for video streaming depends on accurately predicting the download time of video chunks. Existing prediction approaches (i) assume chunk download times are dominated by network throughput; and (ii) apriori cluster sessions (e.g., based on ISP and CDN) and only learn from sessions in the same cluster. We make three contributions. First, through analysis of data from real-world video streaming sessions, we show (i) apriori clustering prevents learning from related clusters; and (ii) factors such as the Time to First Byte (TTFB) are key components of chunk download times but not easily incorporated into existing prediction approaches. Second, we propose Xatu, a new prediction approach that jointly learns a neural network sequence model with an interpretable automatic session clustering method. Xatu learns clustering rules across all sessions it deems relevant, and models sequences with multiple chunk-dependent features (e.g., TTFB) rather than just throughput. Third, evaluations using the above datasets and emulation experiments show that Xatu significantly improves prediction accuracies by 23.8% relative to CS2P (a state-of-the-art predictor). We show Xatu provides substantial performance benefits when integrated with multiple ABR algorithms including MPC (a well studied ABR algorithm), and FuguABR (a recent algorithm using stochastic control) relative to their default predictors (CS2P and a fully connected neural network respectively). Further, Xatu combined with MPC outperforms Pensieve, an ABR based on deep reinforcement learning.

Funder

Cisco Systems

National Science Foundation

Purdue Integrative Data Science Initiative

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture,Safety, Risk, Reliability and Quality,Computer Science (miscellaneous)

Reference72 articles.

1. Can I stream Netflix in ultra hd? https://help.netflix.com/en/node/13444. Can I stream Netflix in ultra hd? https://help.netflix.com/en/node/13444.

2. Chrome Remote Interface. https://github.com/cyrus-and/chrome-remoteinterface. Chrome Remote Interface. https://github.com/cyrus-and/chrome-remoteinterface.

3. DASH IF Test Assets Database. http://testassets.dashif.org/#testvector/list. DASH IF Test Assets Database. http://testassets.dashif.org/#testvector/list.

Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. SODA: An Adaptive Bitrate Controller for Consistent High-Quality Video Streaming;Proceedings of the ACM SIGCOMM 2024 Conference;2024-08-04

2. BONES: Near-Optimal Neural-Enhanced Video Streaming;Proceedings of the ACM on Measurement and Analysis of Computing Systems;2024-05-21

3. Watching Stars in Pixels: The Interplay Of Traffic Shaping and YouTube Streaming QoE over GEO Satellite Networks;Lecture Notes in Computer Science;2024

4. Veritas: Answering Causal Queries from Video Streaming Traces;Proceedings of the ACM SIGCOMM 2023 Conference;2023-09

5. Cross-layer Network Bandwidth Estimation for Low-latency Live ABR Streaming;Proceedings of the 14th Conference on ACM Multimedia Systems;2023-06-07

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3