An Adaptive Bitrate Algorithm Based on Video Classification

doi:10.19678/j.issn.1000-3428.0059790

Abstract

Abstract: The Adaptive Bitrate(ABR) algorithms for streaming media can dynamically adjust the bitrate of video blocks according to network status, and thus improve the user Quality of Experience(QoE).However, the existing algorithms usually ignore the impact of video types on the QoE, resulting in performance degradation.This paper proposes a bitrate selection algorithm, C-ABR, which adapts to different types of videos.Corresponding utilization functions of user experience quality are designed, and the A3C model is trained by using the reinforcement learning algorithm to improve the QoE.The experimental results show that compared with the current typical bitrate self-adaption algorithms, including Pensieve and MPC, the C-ABR method improves the QoE by 22.7% and 50.4%, respectively.

Key words: Quality of Experience(QoE), reinforcement learning, Adaptive Bitrate(ABR) algorithm, stream media, reward function

摘要： 流媒体的码率自适应算法依据网络状态动态调节视频块的码率，提升用户体验质量，但忽略了视频类型的差异对用户体验质量的影响，导致算法性能下降。提出区分视频类型特征的码率选择算法C-ABR。设计相应的用户体验质量效用函数，使用强化学习算法训练模型A3C，提升用户体验质量。实验结果说明，相对于典型的码率自适应算法Pensieve和MPC，C-ABR算法用户体验质量分别提升22.7%和50.4%。

关键词: 体验质量, 强化学习, 码率自适应算法, 流媒体, 激励函数

CLC Number:

TP37

CHEN Zihan, YE Jin, XIAO Qingyu. An Adaptive Bitrate Algorithm Based on Video Classification[J]. Computer Engineering, 2021, 47(12): 118-121,130.

陈梓晗, 叶进, 肖庆宇. 一种基于视频分类的码率自适应算法[J]. 计算机工程, 2021, 47(12): 118-121,130.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0059790

http://www.ecice06.com/EN/Y2021/V47/I12/118

Figures/Tables 7

References

[1] 中国互联网络信息中心.第44次中国互联网络发展状况统计报告[EB/OL].[2020-09-10].http://www.cac.gov.cn. China Internet Network Information Center.The 44th statistical report on Internet development in China[EB/OL].[2020-09-10].http://www.cac.gov.cn. (in Chinese)
[2] Cisco visual networking index:forecast and methodology[EB/OL].[2020-09-10].https://www.cisco.com/c/en/us/solutions/service-provider/index.html.
[3] JIANG J, SEKAR V, ZHANG H.Improving fairness, efficiency, and stability in HTTP-based adaptive video streaming with festive[J].IEEE/ACM Transactions on Networking, 2014, 22(1):326-340.
[4] LIU C H, BOUAZIZI I, GABBOUJ M.Rate adaptation for adaptive http streaming[C]//Proceedings of ACM MMSys ʼ11.New York, USA:ACM Press, 2011:169-174.
[5] SUN Y, YIN X, JIANG J, et al.CS2P:improving video bitrate selection and adaptation with data-driven throughput prediction[C]//Proceedings of ACM SIGCOMMʼ16.New York, USA:ACM Press, 2016:272-285.
[6] ABDELHAK B, ALI C B, ROGER Z.QoE-aware bandwidth broker for HTTP adaptive streaming flows in an SDN-enabled HFC network[J].IEEE Transactions on Broadcasting, 2018, 64(2):575-589.
[7] HUANG T Y, JOHARI R, MCKEOWN N.Downton abbey without the hiccups:buffer-based rate adaptation for HTTP video streaming[C]//Proceedings of ACM SIGCOMM Workshop on Future Human-centric Multimedia Networking.New York, USA:ACM Press, 2013:453-467.
[8] HUANG T Y, JOHARI R, MCKEOWN N, et al.A buffer-based approach to rate adaptation:evidence from a large video streaming service[C]//Proceedings of ACM SIGCOMMʼ14.New York, USA:ACM Press, 2014:187-198.
[9] 潘鹏程, 李国平, 王国中.基于HTTP的流媒体自适应码率切换算法[J].电子测量技术, 2017, 40(9):141-145. PAN P C, LI G P, WANG G Z.HTTP-based adaptive bit rate switching algorithm for streaming media[J].Electronic Measurement Technology, 2017, 40(9):141-145.(in Chinese)
[10] HUANG T C, ZHOU C, ZHANG R X, et al.Comyco:Quality-aware adaptive video streaming via imitation learning[C]//Proceedings of the 27th ACM International Conference on Multimedia.New York, USA:ACM Press, 2019:429-437.
[11] SPITERI K, URGAONKAR R, SITARAMAN P K.BOLA:near-optimal bitrate adaptation for online videos[C]//Proceedings of the 35th Annual IEEE International Conference on Computer Communications.Washington D.C., USA:IEEE Press, 2016:1-9.
[12] SOBHANI A, YASSINE A, SHIRMOHAMMADI S.A video bitrate adaptation and prediction mechanism for HTTP adaptive streaming[J].ACM Transactions on Multimedia Computing Communications & Applications, 2017, 13(2):18-23.
[13] VERGADOS D J, MICHALAS A, SGORA A, et al.FDASH:a fuzzy-based MPEG/DASH adaptation algorithm[J].IEEE Systems Journal, 2016, 10(2):859-868.
[14] TIAN G B, LIU Y.Towards agile and smooth video adaptation in dynamic HTTP streaming[C]//Proceedings of CoNEXTʼ12.Washington D.C., USA:IEEE Press, 2012:109-120.
[15] YIN X, JINDAL A, SEKAR V, et al.A control-theoretic approach for dynamic adaptive video streaming over HTTP[J].ACM SIGCOMM Computer Communication Review, 2015, 45(4):325-338.
[16] MAO H Z, NETRAVALI R, ALIZADEH M.Neural adaptive video streaming with pensieve[C]//Proceedings of SIGCOMMʼ17.New York, USA:ACM Press, 2017:197-210.
[17] HUANG T, YAO X, WU C, et al.Tiyuntsong:a self-play reinforcement learning approach for ABR video streaming[C]//Proceedings of IEEE International Conference on Multimedia and Expo.Washington D.C., USA:IEEE Press, 2019:1678-1683.
[18] ZHANG Y, CLAVERA I, TAI B, et al.Asynchronous methods for model-based reinforcement learning[EB/OL].[2020-09-10].https://arxiv.org/abs/1910.12453v1.
[19] CHUNG J.Playing ATARI with deep reinforcement learning[EB/OL].[2020-09-10].https://arxiv.preprintarxiv/1312.5602.
[20] VAN HASSELT H, GUEZ A, SILVER D.Deep reinforcement learning with double q-learning[EB/OL].[2020-09-10].https://arxiv.org/pdf/1509.06461.pdf.

Please choose a citation manager

Content to export