Understanding the Networking Performance ofWear OS

Author:

Zhu Xiao1,Ethan Guo Yihua2,Nikravesh Ashkan1,Qian Feng3,Mao Z. Morley1

Affiliation:

1. University of Michigan, Ann Arbor, MI, USA

2. Uber Technologies, Inc, San Francisco, CA, USA

3. University of Minnesota, Minneapolis, MN, USA

Abstract

Networking on wearable devices such as smartwatches is becoming increasingly important as fueled by new hardware, OS support, and applications. In this work, we conduct a first in-depth investigation of the networking performance of Wear OS, one of the most popular OSes for wearables. Through carefully designed controlled experiments conducted in a cross-device, cross-protocol, and crosslayer manner, we identify serious performance issues of Wear OS regarding key aspects that distinguish wearable networking from smartphone networking: Bluetooth (BT) performance, smartphone proxying, network interface selection, and BT-WiFi handover. We pinpoint their root causes and quantify their impacts on network performance and application QoE. We further propose practical suggestions to improve wearable networking performance.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture,Software

Reference12 articles.

1. 2017. Cicret Bracelet. https://cicret.com/wordpress/. 2017. Cicret Bracelet. https://cicret.com/wordpress/.

2. 2017. ZenWatch Remote Camera. https://play.google.com/store/apps/details?id= com.asus.rcamera2. 2017. ZenWatch Remote Camera. https://play.google.com/store/apps/details?id= com.asus.rcamera2.

3. Kiryong Ha Zhuo Chen Wenlu Hu Wolfgang Richter Padmanabhan Pillai and Mahadev Satyanarayanan. 2014. Towards wearable cognitive assistance. In MobiSys. ACM. Kiryong Ha Zhuo Chen Wenlu Hu Wolfgang Richter Padmanabhan Pillai and Mahadev Satyanarayanan. 2014. Towards wearable cognitive assistance. In MobiSys. ACM.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3