基于网络流量预测的DASH系统优化

doi:10.19678/j.issn.1000-3428.0057142

摘要/Abstract

摘要： 近年来基于超文本传输协议（HTTP）的自适应视频流量大幅上升，传统HTTP动态自适应流（DASH）速率算法无法准确预测网络吞吐量，导致网络带宽波动，使传输控制协议慢启动并触发抛弃规则，从而降低视频质量。提出一种基于网络流量预测的改进DASH速率算法。将DASH算法分为视频质量选择阶段、视频下载阶段和请求等待阶段，在视频质量选择阶段引入支持向量回归模型和长短期记忆网络预测网络吞吐量，结合缓冲时长选择更优质量的视频片段，在视频下载阶段通过预测实时吞吐量降低触发抛弃规则的次数。仿真结果表明，该算法可自适应流速率并减少抛弃规则的命中次数，有效提高视频体验质量。

关键词: 基于HTTP的动态自适应流, 体验质量, 吞吐量预测, 支持向量回归模型, 长短期记忆网络

Abstract: In recent years,the adaptive video traffic based on Hyper Text Transfer Protocol(HTTP) has increased greatly.The traditional Dynamic Adaptive Streaming over HTTP(DASH) rate algorithm can no longer accurately predict the network throughput,giving rise to the fluctuations of network bandwidth.The fluctuations cause the transmission control protocol slow to start and thus trigger the discarding rules,leading to a decrease in the video quality.This paper proposes an improved DASH rate algorithm based on network traffic prediction.The DASH algorithm is divided into video quality selection stage,video downloading stage and request waiting stage.In the video quality selection stage,the Support Vector Regression(SVR) model and the Long Short-Term Memory(LSTM) network are introduced to predict the network throughput.In addition,the buffer duration is used to select the better quality video clips.In the video downloading stage,the real-time throughput is predicted to reduce the number of times the discarding rules are triggered. Simulation results show that the proposed algorithm can adapt to the streaming rate and reduce the hit times of discarding rules,effectively improving the Quality of Experience(QoE) for video.

Key words: Dynamic Adaptive Streaming over HTTP(DASH), Quality of Experience(QoE), throughput prediction, Support Vector Regression(SVR) model, Long Short-Term Memory(LSTM) network

中图分类号:

TP368.6

耿俊杰, 李晓明, 颜金尧. 基于网络流量预测的DASH系统优化[J]. 计算机工程, 2021, 47(5): 292-300.

GENG Junjie, LI Xiaoming, YAN Jinyao. Optimization of DASH System Based on Network Traffic Prediction[J]. Computer Engineering, 2021, 47(5): 292-300.

https://www.ecice06.com/CN/Y2021/V47/I5/292

参考文献

[1] CISCO.Visual Networking Index[EB/OL].[2019-11-23].https://www.cnbeta.com/articles/tech/696531.htm.
[2] HU Lizhen.Design and implementation of RTSP based embedded streaming media server[D].Wuhan:Huazhong University of Science and Technology,2017.(in Chinese)胡李镇.基于RTSP的嵌入式流媒体服务器设计与实现[D].武汉:华中科技大学,2017.
[3] SCHULZRINNE H,CASNER S,FREDERICK R,et al.RTP:a transport protocol for real-time applications[EB/OL].[2019-11-23].http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.418.7756.
[4] LIN Chaolong.A study on application of network video transmission based on RTP[J].Electronic Engineer,2009,35(12):54-57.(in Chinese)林朝龙.基于RTP的网络视频传输的应用研究[J].信息化研究,2009,35(12):54-57.
[5] KUMAR M V P,MAHAPATRA S.Quality of experience driven rate adaptation for adaptive HTTP streaming[EB/OL].[2019-11-23].https://www.researchgate.net/publication/323204676_Quality_of_Experience_Driven_Rate_Adaptation_for_Adaptive_HTTP_Streaming.
[6] JIN Qixi.Research on HTTP dynamic adaptive streaming media transmission optimization method based on QoE[D].Hangzhou:Zhejiang University,2018.(in Chinese)金栖西.基于QoE的HTTP动态自适应流媒体传输优化方法研究[D].杭州:浙江大学,2018.
[7] KRISHNAN S S,SITARAMAN R K.Video stream quality impacts viewer behavior:inferring causality using quasi-experimental designs[J].IEEE/ACM Transactions on Networking,2013,21(6):2001-2014.
[8] HOU Yonghong,WANG Liwei,XING Jiaming.HTTP-based dynamic adaptive streaming video transmission algorithm[J].Journal of Jilin University(Engineering and Technology Edition),2018,48(4):1244-1253.(in Chinese)侯永宏,王利伟,邢家明.基于HTTP的动态自适应流媒体传输算法[J].吉林大学学报(工学版),2018,48(4):1244-1253.
[9] STOCKHAMMER T.Dynamic adaptive streaming over HTTP:standards and design principles[C]//Proceedings of the 2nd Annual ACM SIGMM Conference on Multimedia Systems.New York,USA:ACM Press,2011:23-25.
[10] LI Jian.A just-in-time encapsulation mechanism for adaptive bit rate video stream[J].Computer and Modernization,2014,30(11):45-48,52.(in Chinese)李建.自适应比特率视频流的适时封装机制[J].计算机与现代化,2014,30(11):45-48,52.
[11] ZOU X K,ERMAN J,GOPALAKRISHNAN V,et al.Can accurate predictions improve video streaming in cellular networks?[C]//Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications.New York,USA:ACM Press,2015:57-62.
[12] YIN X Q,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(5):325-338.
[13] GUO Jianyuan,XIE Zhen,QIN Yong,et al.Short-term abnormal passenger flow prediction based on the fusion of SVR and LSTM[J].IEEE Access,2019,7:42946-42955.
[14] REHMAN A,ZENG K,WANG Z.Display device-adapted video quality of experience assessment[C]//Proceedings of 2015 Conference on Human Vision and Electronic Imaging.[S.l.]:SPIE,2015:1-6.
[15] DASH-industry forum,2014 guidelines for implementation:DASH avc/264 test cases and vectors[EB/OL].[2019-11-23].http://dashif.org/wp-content/uploads/2015/04/dash-avc-264-test-vectors-v09-communityreview.pdf.
[16] LIU C,BOUAZIZI I,HANNUKSELA M M,et al.Rate adaptation for dynamic adaptive streaming over HTTP in content distribution network[J].Signal Processing:Image Communication,2012,27(4):288-311.
[17] MILLER K,QUACCHIO E,GENNARI G,et al.Adaptation algorithm for adaptive streaming over HTTP[C]//Proceedings of 2012 International Conference on Packet Video Workshop.Washington D.C.,USA:IEEE Press,2012:173-178.
[18] OZCINAR C,EKMEKCIOGLU E,KONDOZ A.HTTP adaptive multiview video streaming[M].Berlin,Germany:Springer,2017.
[19] HUANG T Y,JOHARI R,MCKEOWN N,et al.Using the buffer to avoid rebuffers:evidence from a large video streaming service[EB/OL].[2019-11-23].https://arxiv.org/abs/1401.2209.
[20] LI Z,ZHU X,GAHM J,et al.Probe and adapt:rate adaptation for HTTP video streaming at scale[J].IEEE Journal on Selected Areas in Communications,2014,32(4):719-733.
[21] MOK R K P,LUO X,CHAN E W W,et al.QDASH:a QoE-aware DASH system[C]//Proceedings of the 3rd Multimedia Systems Conference.New York,USA:ACM Press,2012:11-22.
[22] SPITERI K,URGAONKAR R,SITARAMAN R K.BOLA:near-optimal bitrate adaptation for online videos[EB/OL].[2019-11-23].https://www.researchgate.net/publication/301898907_BOLA_Near-Optimal_Bitrate_Adaptation_for_Online_Videos.
[23] CHEN Jian.Analysis of user video experience modeling on network side assessment[J].Modern Industrial Economy and Informationization,2018,8(10):23-25.(in Chinese)陈坚.网络侧评估用户视频体验建模分析[J].现代工业经济和信息化,2018,8(10):23-25.
[24] JIANG Ming,WU chunming,ZHANG Min,et al.Research on the comparison of time series models for network traffic prediction[J].Acta Electronica Sinica,2009,37(11):2353-2358.(in Chinese)姜明,吴春明,张旻,等.网络流量预测中的时间序列模型比较研究[J].电子学报,2009,37(11):2353-2358.
[25] JIANG J,PAPAVASSILIOU S.Enhancing network traffic prediction and anomaly detection via statistical network traffic separation and combination strategies[J].Computer Communications,2006,29(10):1627-1638.
[26] CIPTANINGTYAS H T,FATICHAH C,SABILA A.Network traffic anomaly prediction using artificial neural network[EB/OL].[2019-11-23].https://aip.scitation.org/doi/10.1063/1.4976874.
[27] FANG Jie,ZHOU Qingbiao,WU Xide,et al.Network traffic prediction model based on Catfish-PSO-SVM[J].Journal of Networks,2013,8(11):2534-2540.
[28] ZHOU Xiaolei,WANG Wanliang,CHEN Weijie.Network traffic prediction model based on wavelet transform and optimised SVM[J].Computer Applications and Software,2011,28(2):34-36,59.(in Chinese)周晓蕾,王万良,陈伟杰.基于小波变换和优化的SVM的网络流量预测模型[J].计算机应用与软件,2011,28(2):34-36,59.
[29] KHARAT J P.Comparative study of various neural network architectures for MPEG-4 video traffic prediction[J].International Journal of Advances in Applied Sciences,2017,6(4):283-285.
[30] FU Rui,ZHANG Zuo,LI Li.Using LSTM and GRU neural network methods for traffic flow prediction[EB/OL].[2019-11-23].https://www.researchgate.net/publication/312402649_Using_LSTM_and_GRU_neural_network_methods_for_traffic_flow_prediction.
[31] BENTALEB A,BEGEN A C,ZIMMERMANN R.SDNDASH:improving QoE of HTTP adaptive streaming using software defined networking[C]//Proceedings of the 24th ACM International Conference on Multimedia.New York,USA:ACM Press,2016:1296-1305.
[32] DASH.js:a reference client implementation for the playback of MPEG DASH via javascript and compliant browsers[EB/OL].[2019-11-23].https://github.com/Dash-Industry-Forum/dash.js/wiki.

选择文件类型/文献管理软件名称

选择包含的内容