{"title":"Learning Based Deadline Aware Congestion Control","authors":"Rongji Liao, Jinyao Yan, Tao Lin, Yuhao Chen","doi":"10.1145/3469393.3469675","DOIUrl":null,"url":null,"abstract":"A large variety of applications are deadline aware such as 360 degree VR (Virtual Reality), video conference and online gaming. In this paper, we propose a congestion control algorithm using deep reinforcement learning named DRL-CC to make the data arrive before the deadline. The initial experiments validate that our method dramatically increases the number of packets arrived before the deadline compared with existing algorithms.","PeriodicalId":291942,"journal":{"name":"5th Asia-Pacific Workshop on Networking (APNet 2021)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"5th Asia-Pacific Workshop on Networking (APNet 2021)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3469393.3469675","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
A large variety of applications are deadline aware such as 360 degree VR (Virtual Reality), video conference and online gaming. In this paper, we propose a congestion control algorithm using deep reinforcement learning named DRL-CC to make the data arrive before the deadline. The initial experiments validate that our method dramatically increases the number of packets arrived before the deadline compared with existing algorithms.