用户密集环境下基于边缘智能的直播视频传输优化机制

doi:10.11959/j.issn.1000-436x.2023232

通信学报 ›› 2023, Vol. 44 ›› Issue (11): 55-66.doi: 10.11959/j.issn.1000-436x.2023232

• 专题：复杂环境下分布式边缘智能 • 上一篇

用户密集环境下基于边缘智能的直播视频传输优化机制

顾晓丹, 吴文甲, 凌振

东南大学计算机科学与工程学院，江苏南京 211189

修回日期:2023-11-01 出版日期:2023-11-01 发布日期:2023-11-01
作者简介:顾晓丹（1987− ），女，江苏常州人，博士，东南大学讲师，主要研究方向为移动互联网、网络安全、匿名通信等
吴文甲（1983− ），男，江苏盐城人，博士，东南大学副教授，主要研究方向为移动物联网、智能无线网络等
凌振（1982− ），男，江苏宜兴人，博士，东南大学教授，主要研究方向为移动物联网、网络安全与隐私、可信计算等
基金资助:
国家自然科学基金资助项目(62072102);国家自然科学基金资助项目(62132009);国家自然科学基金资助项目(62102084)

Live video transmission optimization mechanism based on edge intelligence in high client-density environment

Xiaodan GU, Wenjia WU, Zhen LING

School of Computer Science and Engineering, Southeast University, Nanjing 211189, China

Revised:2023-11-01 Online:2023-11-01 Published:2023-11-01
Supported by:
The National Natural Science Foundation of China(62072102);The National Natural Science Foundation of China(62132009);The National Natural Science Foundation of China(62102084)

摘要/Abstract

摘要：

针对传统直播视频传输优化机制部署在服务器侧，无法快速响应用户终端所处的无线网络环境动态变化的问题，提出基于边缘智能的直播视频传输优化机制S-Edge。该机制部署在基于OpenWrt的无线接入点上，综合利用占空比、信噪比等无线信道状态信息，基于模糊逻辑理论对终端优先级及传输速率进行智能决策，并通过分层令牌桶的主动队列管理和业务需求驱动的无线传输速率自适应控制技术，实现直播视频终端业务的实时调度。为了验证所提机制 S-Edge 的有效性和性能，在真实场景下搭建基于多射频接口的硬件实验平台并开展用户密集无线网络环境下的实验。实验结果表明，S-Edge可以显著降低平均时延和丢包率，有效提升用户密集环境下直播视频传输业务的服务质量指标。

关键词: 无线局域网, 直播视频传输, 用户密集, 边缘智能

Abstract:

The traditional live video transmission optimization mechanism is deployed on the server side, which cannot quickly respond to the dynamic changes of the user’s wireless network environment.To address this problem, a live video transmission optimization mechanism based on edge intelligence called S-Edge was proposed.It was deployed on the OpenWrt-based wireless access point, and comprehensively utilized the wireless channel state information such as airtime utilization and signal-to-noise ratio to make intelligent decisions on terminal priority and transmission rate based on fuzzy logic theory.Furthermore, the active queue management with hierarchical token bucket and service demand-driven wireless transmission rate adaptive control technologies were introduced to realize the real-time scheduling of live video data.In order to verify the effectiveness and performance of the proposed mechanism, a high client-density environment was built through user clusters based on multi-radio interfaces in the real-world scenario.Experimental results show that S-Edge can significantly reduce the average delay and packet loss rate, which meets QoS requirements of live video transmission services in the high client-density environment.

Key words: WLAN, live video transmission, high client-density, edge intelligence

中图分类号:

TP393

顾晓丹, 吴文甲, 凌振. 用户密集环境下基于边缘智能的直播视频传输优化机制[J]. 通信学报, 2023, 44(11): 55-66.

Xiaodan GU, Wenjia WU, Zhen LING. Live video transmission optimization mechanism based on edge intelligence in high client-density environment[J]. Journal on Communications, 2023, 44(11): 55-66.

图/表 10

图1

图2

图3

表1

图4

图5

图6

表2

图7

图8

参考文献 22

[1]	HSIEH P C , LIU X , HOU I H . Fresher content or smoother playback:a Brownian-approximation framework for scheduling real-time wireless video streams[C]// Proceedings of the Twenty-First International Symposium on Theory,Algorithmic Foundations,and Protocol Design for Mobile Networks and Mobile Computing. New York:ACM Press, 2020: 41-50.
[2]	ZHANG H H , ZHOU A F , LU J M ,et al. OnRL:improving mobile video telephony via online reinforcement learning[C]// Proceedings of the 26th Annual International Conference on Mobile Computing and Networking. New York:ACM Press, 2020: 1-14.
[3]	ZHANG C , LIU J C , WANG Z ,et al. Look ahead at the first-mile in livecast with crowdsourced highlight prediction[C]// Proceedings of IEEE Conference on Computer Communications. Piscataway:IEEE Press, 2020: 1143-1152.
[4]	BENTALEB A , N AKCAY M , LIM M ,et al. Catching the moment with LoL- in twitch-like low-latency live streaming platforms[J]. IEEE Transactions on Multimedia, 2021,24: 2300-2314.
[5]	MU P K , ZHENG J K , LUAN T H ,et al. AMIS:edge computing based adaptive mobile video streaming[C]// Proceedings of IEEE Conference on Computer Communications. Piscataway:IEEE Press, 2021: 1-10.
[6]	WANG F X , ZHANG C , WANG F ,et al. Intelligent edge-assisted crowdcast with deep reinforcement learning for personalized QoE[C]// Proceedings of IEEE Conference on Computer Communications. Piscataway:IEEE Press, 2019: 910-918.
[7]	LUO Z X , WANG Z L , HU M ,et al. LiveSR:enabling universal HD live video streaming with crowdsourced online learning[J]. IEEE Transactions on Multimedia, 2023,25: 2788-2798.
[8]	ALI R , SHAHIN N , ZIKRIA Y B ,et al. Deep reinforcement learning paradigm for performance optimization of channel observation-based MAC protocols in dense WLANs[J]. IEEE Access, 2018,7: 3500-3511.
[9]	胡雨涵 . 视频直播传输算法的优化与系统实现[D]. 北京:北京邮电大学, 2022.
	HU Y H . Optimization and system implementation of live video transmission algorithm[D]. Beijing:Beijing University of Posts and Telecommunications, 2022.
[10]	GUTTERMAN C , FRIDMAN B , GILLILAND T ,et al. Stallion:video adaptation algorithm for low-latency video streaming[C]// Proceedings of the 11th ACM Multimedia Systems Conference. New York:ACM Press, 2020: 327-332.
[11]	乔春雨 . 面向真实环境自适应视频流的用户体验优化研究[D]. 北京:清华大学, 2021.
	QIAO C Y . Research on user experience optimization of adaptive video streaming for real environment[D]. Beijing:Tsinghua University, 2021.
[12]	BHATTACHARYYA R , BURA A , RENGARAJAN D ,et al. QFlow:a reinforcement learning approach to high QoE video streaming over wireless networks[C]// Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and Computing. New York:ACM Press, 2019: 251-260.
[13]	BABU M M , REDDY P C , SAM R P . A novel cross-layer based priority aware scheduling scheme for QoE guaranteed video transmission over wireless networks[J]. Multimedia Tools and Applications, 2022,81(20): 28129-28164.
[14]	MAO H Z , NETRAVALI R , ALIZADEH M . Neural adaptive video streaming with pensieve[C]// Proceedings of the Conference of the ACM Special Interest Group on Data Communication. New York:ACM Press, 2017: 197-210.
[15]	BALAN D G , POTORAC D A . Linux HTB queuing discipline implementations[C]// Proceedings of First International Conference on Networked Digital Technologies. Piscataway:IEEE Press, 2009: 122-126.
[16]	OTT H , MILLER K , WOLISZ A . Simulation framework for HTTP-based adaptive streaming applications[C]// Proceedings of the Workshop on NS-3. New York:ACM Press, 2017: 95-102.
[17]	RACA D , SANI Y , SREENAN C J ,et al. DASHbed:a testbed framework for large scale empirical evaluation of real-time DASH in wireless scenarios[C]// Proceedings of the 10th ACM Multimedia Systems Conference. New York:ACM Press, 2019: 285-290.
[18]	YI G , YANG D , BENTALEB A ,et al. The ACM multimedia 2019 live video streaming grand challenge[C]// Proceedings of the 27th ACM International Conference on Multimedia. New York:ACM Press, 2019: 2622-2626.
[19]	CAPDEHOURAT G , áLVAREZ G , áLVAREZ M ,et al. High density emulation platform for Wi-Fi performance testing[J]. Ad Hoc Networks, 2018,70: 1-13.
[20]	ARIF T Y . Evaluation of the minstrel-HT rate adaptation algorithm in IEEE 802.11n WLANs[J]. International Journal of Simulation:Systems,Science ＆ Technology, 2017,18(1): 1-7.
[21]	MENDEL J M . Fuzzy logic systems for engineering:a tutorial[J]. Proceedings of the IEEE, 1995,83(3): 345-377.
[22]	YIN X Q , JINDAL A , SEKAR V ,et al. A control-theoretic approach for dynamic adaptive video streaming over HTTP[C]// Proceedings of the ACM Conference on Special Interest Group on Data Communication. New York:ACM Press, 2015: 325-338.

规则	模糊规则条件（IF）					模糊规则结果（THEN）
规则	Th	Ls	Sr	Ns	Au	Pr	MCS index
R₁	L	L	M	M	H	L	M
R₂	L	H	L	L	M	H	L
R₃	M	H	L	L	M	M	L
R₄	H	L	H	H	L	M	H
R₅	H	L	H	H	L	M	M

型号和配置	操作系统	功能
一台x86 PC	Ubuntu 20.04 LTS 64 位	部署在公网的文件下载服务器
一台x86 PC Intel 3168/8265/9260ac无线网卡共18块	Ubuntu 18.04 LTS 64 位	作为基于多射频接口的用户终端集群，用以构建用户密集环境
一台WPQ864开发板（配备QCA9984网卡）	OpenWrt 19.07.8	作为AP，建立和管理Wi-Fi 热点

用户密集环境下基于边缘智能的直播视频传输优化机制

Live video transmission optimization mechanism based on edge intelligence in high client-density environment

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 15

Metrics

推荐阅读 0

[1]	李云, 高倩, 姚枝秀, 夏士超, 梁吉申. 移动边缘计算中智能服务编排和算网资源分配联合优化方法[J]. 通信学报, 2023, 44(7): 51-63.
[2]	陶梅霞, 王栋, 孙瑞, 张乃夫. 联邦学习中基于时分多址接入的用户调度策略[J]. 通信学报, 2021, 42(6): 1-29.
[3]	张思成,林云,涂涯,ShiwenMao. 基于轻量级深度神经网络的电磁信号调制识别技术[J]. 通信学报, 2020, 41(11): 12-21.
[4]	李华亮,钱志鸿,田洪亮. 基于核函数特征提取的室内定位算法研究[J]. 通信学报, 2017, 38(1): 158-167.
[5]	张琦，赵林靖，李建东. 基于QoS保障的密集WLAN多维资源分配算法[J]. 通信学报, 2014, 35(3): 17-156.
[6]	张琦,赵林靖,李建东. 基于QoS保障的密集WLAN多维资源分配算法[J]. 通信学报, 2014, 35(3): 150-156.
[7]	冀保峰1,2，宋康1，黄永明1，杨绿溪1. 基于IEEE 802.11ac的多用户MIMO传输方案的优化设计及其性能分析[J]. 通信学报, 2013, 34(5): 11-106.
[8]	冀保峰,宋康,黄永明,杨绿溪. 基于IEEE 802.11ac的多用户MIMO传输方案的优化设计及其性能分析[J]. 通信学报, 2013, 34(5): 96-106.
[9]	杨春刚,徐超,盛敏,李建东,李红艳. 认知Wi-Fi 2.0网络：未来智能无线局域网[J]. 通信学报, 2012, 33(Z2): 71-80.
[10]	宋震龙,蒋刚毅,黄晁,郁梅,张家乐. 基于偏度-峰度检验的无线局域网室内定位算法[J]. 通信学报, 2012, 33(5): 99-105.
[11]	吴大鹏,武穆清,甄岩. 有效提高吞吐量的数据帧发送策略WLAN[J]. 通信学报, 2010, 31(2): 10-17.
[12]	黄家纬,王建新. 多速率802.11 WLAN中时间公平的主动队列管理算法[J]. 通信学报, 2009, 30(2): 35-41.
[13]	李亚晖,李凤华,杨卫东,马建峰. 可证明安全的异构无线网络认证协议[J]. 通信学报, 2007, 28(11): 21-26.
[14]	冯辉,王挺,胡波. 有效提高无线局域网信道可用带宽的MAC机制[J]. 通信学报, 2006, 27(7): 94-99.
[15]	盛凌志,皇甫伟,雷文,吴志美. 多类别终端无线局域网实时业务性能研究[J]. 通信学报, 2006, 27(4): 16-22.