Instant Messaging Meets Video Conferencing: Studying the Performance of IM Video Calls

Laurenz Grote, Ike Kunze, Constantin Sander, Klaus Wehrle
{"title":"Instant Messaging Meets Video Conferencing: Studying the Performance of IM Video Calls","authors":"Laurenz Grote, Ike Kunze, Constantin Sander, Klaus Wehrle","doi":"10.23919/TMA58422.2023.10199019","DOIUrl":null,"url":null,"abstract":"Video conferencing applications typically use UDP and often implement their own congestion control. Research studying these custom algorithms generally finds that they do react to congestion and can hold their own against competing TCP flows. However, these works focus on applications specializing in video conferencing, neglecting those that only offer video conferencing as one of many features, such as many instant messengers. While these instant messaging-based video call applications (IMVCAs) may opt to use standardized frameworks, such as WebRTC, their actual implementations and behaviors are wildly unknown. In this paper, we thus set out to study the behavior of three popular IMVCAs, analyzing their interplay with TCP and the impact on QoE. We find that the surveyed IMVCAs (Signal, Telegram, WhatsApp) are TCP-friendly, i.e., they do not choke TCP. However, their per-app behavior differs significantly and no app equals the other: Signal and Telegram, e.g., take TCP-friendliness too far, yielding up to 90 % of their bandwidth. This results in severe QoE detriments in the form of drastically reduced sending rates and visual quality. As Signal is known to use WebRTC, this finding suggests that the current variant might be too conservative for coexisting with TCP. In contrast, WhatsApp counters congestion by filling queues to avoid losing bandwidth. Overall, IMVCAs do not keep up with the performance of specialized applications.","PeriodicalId":394676,"journal":{"name":"2023 7th Network Traffic Measurement and Analysis Conference (TMA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 7th Network Traffic Measurement and Analysis Conference (TMA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/TMA58422.2023.10199019","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Video conferencing applications typically use UDP and often implement their own congestion control. Research studying these custom algorithms generally finds that they do react to congestion and can hold their own against competing TCP flows. However, these works focus on applications specializing in video conferencing, neglecting those that only offer video conferencing as one of many features, such as many instant messengers. While these instant messaging-based video call applications (IMVCAs) may opt to use standardized frameworks, such as WebRTC, their actual implementations and behaviors are wildly unknown. In this paper, we thus set out to study the behavior of three popular IMVCAs, analyzing their interplay with TCP and the impact on QoE. We find that the surveyed IMVCAs (Signal, Telegram, WhatsApp) are TCP-friendly, i.e., they do not choke TCP. However, their per-app behavior differs significantly and no app equals the other: Signal and Telegram, e.g., take TCP-friendliness too far, yielding up to 90 % of their bandwidth. This results in severe QoE detriments in the form of drastically reduced sending rates and visual quality. As Signal is known to use WebRTC, this finding suggests that the current variant might be too conservative for coexisting with TCP. In contrast, WhatsApp counters congestion by filling queues to avoid losing bandwidth. Overall, IMVCAs do not keep up with the performance of specialized applications.
即时消息与视频会议的结合:研究即时消息视频通话的性能
视频会议应用程序通常使用UDP,并且经常实现自己的拥塞控制。对这些自定义算法的研究通常发现,它们确实对拥塞做出反应,并且可以在竞争的TCP流中保持自己的状态。然而,这些工作主要集中在专门用于视频会议的应用程序上,而忽略了那些仅提供视频会议作为众多功能之一的应用程序,例如许多即时通讯工具。虽然这些基于即时消息的视频呼叫应用程序(imvca)可能会选择使用标准化框架,如WebRTC,但它们的实际实现和行为却非常未知。在本文中,我们着手研究三种流行的imvca的行为,分析它们与TCP的相互作用以及对QoE的影响。我们发现调查的imvca (Signal, Telegram, WhatsApp)是TCP友好的,即它们不会阻塞TCP。然而,他们的每个应用程序的行为有很大的不同,没有一个应用程序是等同的:例如,Signal和Telegram在tcp友好性方面走得太远了,提供了高达90%的带宽。这将导致严重的QoE损害,其形式是大幅降低发送速率和视觉质量。由于Signal已知使用WebRTC,这一发现表明,当前的变体可能过于保守,无法与TCP共存。相比之下,WhatsApp通过填充队列来应对拥塞,以避免带宽损失。总的来说,imvca不能跟上专门应用程序的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信