TransFetch: A Viewing Behavior Driven Video Distribution Framework in Public Transport

2016 IEEE 41st Conference on Local Computer Networks (LCN) Pub Date : 2016-12-22 DOI:10.1109/LCN.2016.27

Fangzhou Jiang, Zhi Liu, Kanchana Thilakarathna, Zhenyu Li, Yusheng Ji, A. Seneviratne

{"title":"TransFetch: A Viewing Behavior Driven Video Distribution Framework in Public Transport","authors":"Fangzhou Jiang, Zhi Liu, Kanchana Thilakarathna, Zhenyu Li, Yusheng Ji, A. Seneviratne","doi":"10.1109/LCN.2016.27","DOIUrl":null,"url":null,"abstract":"Mobile video traffic is exploding and it is particularly challenging to stream video when high density of users are \"on the move\", e.g., in public transport systems. It becomes increasingly problematic as video traffic is predicted to account for more than 80% of Internet traffic by 2019. This will be exacerbated by factors such as cellular network coverage issues and unstable network throughput due to high speed mobility. By exploiting the predictable public transport mobility patterns, spatio-temporal correlation of user interests and users' video viewing behaviors, we proposed TransFetch which uses intelligent caching on-board the public transport vehicles as well as a novel video chunk placement algorithm. We show through extensive simulations, that TransFetch reduces the system cellular data usage by up to 45% and improves the quality of video streaming by up to 35%. Finally, we demonstrate the practical feasibility of TransFetch by implementing caching units on a Raspberry-Pi and a mobile app on an Android device.","PeriodicalId":6864,"journal":{"name":"2016 IEEE 41st Conference on Local Computer Networks (LCN)","volume":"26 1","pages":"147-155"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE 41st Conference on Local Computer Networks (LCN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/LCN.2016.27","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 9

Abstract

Mobile video traffic is exploding and it is particularly challenging to stream video when high density of users are "on the move", e.g., in public transport systems. It becomes increasingly problematic as video traffic is predicted to account for more than 80% of Internet traffic by 2019. This will be exacerbated by factors such as cellular network coverage issues and unstable network throughput due to high speed mobility. By exploiting the predictable public transport mobility patterns, spatio-temporal correlation of user interests and users' video viewing behaviors, we proposed TransFetch which uses intelligent caching on-board the public transport vehicles as well as a novel video chunk placement algorithm. We show through extensive simulations, that TransFetch reduces the system cellular data usage by up to 45% and improves the quality of video streaming by up to 35%. Finally, we demonstrate the practical feasibility of TransFetch by implementing caching units on a Raspberry-Pi and a mobile app on an Android device.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

TransFetch:公共交通中观看行为驱动的视频分发框架

移动视频流量呈爆炸式增长，当高密度用户“在移动”时，例如在公共交通系统中，流媒体视频尤其具有挑战性。到2019年，视频流量预计将占互联网流量的80%以上，这将变得越来越成问题。由于高速移动，蜂窝网络覆盖问题和不稳定的网络吞吐量等因素将加剧这种情况。利用可预测的公共交通出行模式、用户兴趣和视频观看行为的时空相关性，提出了基于公共交通车辆智能缓存的TransFetch算法以及一种新的视频块放置算法。我们通过大量的模拟表明，TransFetch将系统蜂窝数据使用量减少了45%，并将视频流质量提高了35%。最后，我们通过在树莓派和Android设备上的移动应用程序上实现缓存单元来演示TransFetch的实际可行性。

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分钟内获得全文去求助

来源期刊

2016 IEEE 41st Conference on Local Computer Networks (LCN)

自引率

0.00%

发文量

期刊最新文献

Message from the General Chair Message from the general chair Best of Both Worlds: Prioritizing Network Coding without Increased Space Complexity Controlling Network Latency in Mixed Hadoop Clusters: Do We Need Active Queue Management? TransFetch: A Viewing Behavior Driven Video Distribution Framework in Public Transport