Abstract
In this paper, we propose a novel algorithm for video bitrate adaptation in HTTP Adaptive Streaming (HAS), based on online learning. The proposed algorithm, named Learn2Adapt (L2A), is shown to provide a robust bitrate adaptation strategy which, unlike most of the state-of-the-art techniques, does not require parameter tuning, channel model assumptions, or application-specific adjustments. These properties make it very suitable for mobile users, who typically experience fast variations in channel characteristics. Experimental results, over real 4G traffic traces, show that L2A improves on the overall Quality of Experience (QoE) and in particular the average streaming bitrate, a result obtained independently of the channel and application scenarios.
- [1] . dash.js. https://github.com/Dash-Industry-Forum/dash.js.Google Scholar
- [2] . 2013. Server-based traffic shaping for stabilizing oscillating adaptive streaming players. In Proc. ACM NOSSDAV.Google Scholar
- [3] . 2020. QoE-Fair DASH video streaming using server-side reinforcement learning. ACM TOMM (
June 2020). Google ScholarDigital Library
- [4] . 2018. Online convex optimization and no-regret learning: Algorithms, guarantees and applications. arXiv e-prints (2018).Google Scholar
- [5] . 2018. ORL-SDN: Online reinforcement learning for SDN-Enabled HTTP adaptive streaming. ACM TOMM (
Aug. 2018). Google ScholarDigital Library
- [6] . 2019. A survey on bitrate adaptation schemes for streaming media over HTTP. IEEE Communications Surveys Tutorials 21, 1 (2019).Google Scholar
Cross Ref
- [7] . 2020. Performance analysis of ACTE: A bandwidth prediction method for low-latency chunked streaming. ACM TOMM (
June 2020). Google ScholarDigital Library
- [8] . 2020. DQ-DASH: A queuing theory approach to distributed adaptive video streaming. ACM TOMM (
March 2020). Google ScholarDigital Library
- [9] . 2018. SABR: Network-Assisted content distribution for QoE-Driven ABR Video Streaming. ACM Trans. Multimedia Comput. Commun. Appl. 14, 2s, Article
32 (April 2018), 25 pages. https://doi.org/10.1145/3183516 Google ScholarDigital Library
- [10] . 2015. Optimizing HTTP-Based adaptive streaming in vehicular environment using Markov decision process. IEEE Trans. on Multimedia 17, 12 (
Dec. 2015).Google ScholarDigital Library
- [11] . 2018. A generic approach to video buffer modeling using discrete-time analysis. ACM TOMM (
April 2018). Google ScholarDigital Library
- [12] . 2017. An online convex optimization approach to proactive network resource allocation. IEEE Trans. on Signal Processing (
Dec. 2017).Google ScholarDigital Library
- [13] . 2017. An online convex optimization approach to proactive network resource allocation. IEEE Transactions on Signal Processing (
Dec 2017).Google ScholarDigital Library
- [14] . 2019. Forecast and trends, 2017–2022. White Paper (
Feb. 2019).Google Scholar - [15] . 2019. Global mobile data traffic forecast update, 2017–2022. White Paper (
Feb. 2019).Google Scholar - [16] . 2013. Design of a Q-learning-based client quality selection algorithm for HTTP adaptive video streaming. In Proc. Adaptive and Learning Agents Workshop, part of AAMAS.Google Scholar
- [17] . 2017. Design and performance evaluation of network-assisted control strategies for HTTP adaptive streaming. ACM TOMM (
June 2017). Google ScholarDigital Library
- [18] . 2017. D-DASH: A deep Q-Learning framework for DASH video streaming. IEEE Trans. on Cognitive Communications and Networking 3, 4 (
Dec. 2017).Google ScholarCross Ref
- [19] . 2020. Quality-Aware neural adaptive video streaming with lifelong imitation learning. IEEE Journal on Selected Areas in Communications 38, 10 (2020), 2324–2342. https://doi.org/10.1109/JSAC.2020.3000363Google Scholar
Cross Ref
- [20] . 2019. Hindsight: Evaluate video bitrate adaptation at scale. In Proc. ACM MMSys. Google Scholar
Digital Library
- [21] . 2014. A buffer-based approach to rate adaptation: Evidence from a large video streaming service. In Proc. ACM Conf. on SIGCOMM. Google Scholar
Digital Library
- [22] . 2018. Common media application format CMAF). International Standard 23000-19:2018 (
Jan. 2018).Google Scholar - [23] . 2014. Improving fairness, efficiency, and stability in HTTP-Based adaptive video streaming with festive. IEEE/ACM Trans. on Networking 22, 1 (
Feb. 2014). Google ScholarDigital Library
- [24] . 2017. A comparative case study of HTTP adaptive streaming algorithms in mobile networks. In Proc. ACM NOSSDAV. Google Scholar
Digital Library
- [25] . 2020. Online learning for low-latency adaptive streaming. In Proceedings of ACM MMSys (MMSys’20). Google Scholar
Digital Library
- [26] . 2019. Online learning for robust adaptive video streaming in mobile networks. CoRR abs/1905.11705 (2019). arXiv:1905.11705. http://arxiv.org/abs/1905.11705.Google Scholar
- [27] . 2019. XMAS: An efficient mobile adaptive streaming scheme based on traffic shaping. IEEE Trans. on Multimedia 21, 2 (
Feb 2019). Google ScholarDigital Library
- [28] . 2017. A survey of rate adaptation techniques for dynamic adaptive streaming over HTTP. IEEE Communications Surveys Tutorials 19, 3 (2017).Google Scholar
Digital Library
- [29] . 2014. Probe and adapt: Rate adaptation for HTTP video streaming at scale. IEEE Journal on Selected Areas of Communication (
Apr. 2014).Google ScholarCross Ref
- [30] . 2019. Cautious regret minimization: Online optimization with long-term budget constraints. In Proc. ICML.Google Scholar
- [31] . 2019. No regret in cloud resources reservation with violation guarantees. In Proc. IEEE INFOCOM.Google Scholar
- [32] . 2017. Neural adaptive video streaming with Pensieve. In Proc. ACM SIGCOM. Google Scholar
Digital Library
- [33] . 2019. Online power optimization in feedback-limited, dynamic and unpredictable IoT networks. IEEE Trans. on Signal Processing (2019).Google Scholar
Cross Ref
- [34] . 2017. HTTP adaptive streaming with indoors-outdoors detection in mobile networks. In Proc. IEEE INFOCOM Workshops.Google Scholar
- [35] . 2017. Online convex optimization with time-varying constraints. arXiv e-prints (2017).Google Scholar
- [36] . 2019. Quality-Aware strategies for optimizing ABR video streaming QoE and reducing data usage. In Proceedings of the 10th ACM Multimedia Systems Conference (Amherst, Massachusetts) (
MMSys’19 ). Association for Computing Machinery, New York, NY, USA, 189-200. https://doi.org/10.1145/3304109.3306231 Google ScholarDigital Library
- [37] . 2020. A control theoretic approach to ABR video streaming: A fresh look at PID-Based rate adaptation. IEEE Transactions on Mobile Computing 19, 11 (2020), 2505–2519. https://doi.org/10.1109/TMC.2019.2929125Google Scholar
Cross Ref
- [38] . 2018. Beyond throughput: A 4G LTE dataset with channel and context metrics. In Proc. ACM MMSys.Google Scholar
- [39] . 2019. Empowering video players in cellular: Throughput prediction from radio network measurements. In Proceedings of the 10th ACM Multimedia Systems Conference (Amherst, Massachusetts) (
MMSys’19 ). Association for Computing Machinery, New York, NY, USA, 201–212. https://doi.org/10.1145/3304109.3306233 Google ScholarDigital Library
- [40] . 2015. A survey on quality of experience of HTTP adaptive streaming. IEEE Communications Surveys Tutorials 17, 1 (2015).Google Scholar
Digital Library
- [41] . 2012. Online learning and online convex optimization. Foundations and Trends on Machine Learning (2012). Google Scholar
Digital Library
- [42] . 2018. A survey of emerging concepts and challenges for QoE management of multimedia services. ACM TOMM (
May 2018). Google ScholarDigital Library
- [43] . 2011. The MPEG-DASH standard for multimedia streaming over the internet. IEEE MultiMedia (2011). Google Scholar
Digital Library
- [44] . 2019. From theory to practice: Improving bitrate adaptation in the DASH reference player. ACM TOMM (
July 2019). Google ScholarDigital Library
- [45] . 2016. BOLA: Near-optimal bitrate adaptation for online videos. In IEEE INFOCOM.Google Scholar
- [46] . 2020. Learn2Adapt-LowLatency demo. Retrieved February 3, 2021 from http://reference.dashif.org/dash.js/nightly/samples/low-latency/l2all_index.html.Google Scholar
- [47] . 2020. Learn2Adapt-LowLatency source-code. Retrieved February 3, 2021 from https://github.com/Dash-Industry-Forum/dash.js/blob/development/src/streaming/rules/abr/L2ARule.js.Google Scholar
- [48] . 2018. Classifying flows and buffer state for YouTube’s HTTP adaptive streaming service in mobile networks. In Proc. ACM MMSys. Google Scholar
Digital Library
- [49] . 2018. Problem-Adapted artificial intelligence for online network optimization. preprint arXiv:1805.12090 (2018).Google Scholar
- [50] . 2015. piStream: Physical layer informed adaptive video streaming over LTE. In Proc. ACM MobiCom. Google Scholar
Digital Library
- [51] . 2019. HTTP/2-Based frame discarding for low-latency adaptive video streaming. ACM TOMM (
Feb. 2019). Google ScholarDigital Library
- [52] . 2019. QoE for mobile clients with segment-aware rate adaptation algorithm for DASH video streaming. ACM TOMM (
June 2019).Google ScholarDigital Library
- [53] . 2015. A control-theoretic approach for dynamic adaptive video streaming over HTTP. In Proc. ACM SIGCOMM 14.Google Scholar
- [54] . 2020. Enabling adaptive bitrate algorithms in hybrid CDN/P2P Networks. In Proceedings of the 11th ACM Multimedia Systems Conference (Istanbul, Turkey) (
MMSys’20 ). Association for Computing Machinery, New York, NY, USA, 54–65. https://doi.org/10.1145/3339825.3391859 Google ScholarDigital Library
- [55] . 2020. Energy considerations for ABR video streaming to smartphones: Measurements, models and insights. In Proceedings of the 11th ACM Multimedia Systems Conference (Istanbul, Turkey) (
MMSys’20 ). Association for Computing Machinery, New York, NY, USA, 153–165. https://doi.org/10.1145/3339825.3391867 Google ScholarDigital Library
- [56] . 2018. Multi-codec DASH dataset. In Proc. ACM MMSys. Google Scholar
Digital Library
- [57] . 2016. mDASH: A Markov decision-based rate adaptation approach for dynamic HTTP streaming. IEEE Trans. on Multimedia (
April 2016).Google ScholarDigital Library
- [58] . 2003. Online convex programming and generalized infinitesimal gradient ascent. In Proc. ICML. Google Scholar
Digital Library
Index Terms
Online Learning for Adaptive Video Streaming in Mobile Networks
Recommendations
Online learning for low-latency adaptive streaming
MMSys '20: Proceedings of the 11th ACM Multimedia Systems ConferenceAchieving low-latency is paramount for live streaming scenarios, that are now-days becoming increasingly popular. In this paper, we propose a novel algorithm for bitrate adaptation in HTTP Adaptive Streaming (HAS), based on Online Convex Optimization (...
Adaptive scalable video streaming in wireless networks
MMSys '12: Proceedings of the 3rd Multimedia Systems ConferenceIn this paper, we investigate the optimal streaming strategy for dynamic adaptive streaming over HTTP (DASH). Specifically, we focus on the rate adaptation algorithm for streaming scalable video (H.264/SVC) in wireless networks. We model the rate ...
Feedback control for adaptive live video streaming
MMSys '11: Proceedings of the second annual ACM conference on Multimedia systemsMultimedia content feeds an ever increasing fraction of the Internet traffic. Video streaming is one of the most important applications driving this trend. Adaptive video streaming is a relevant advancement with respect to classic progressive download ...






Comments