EdgeKE: An On-Demand Deep Learning IoT System for Cognitive Big Data on Industrial Edge Devices

物联网 人工神经网络 工业4.0 智慧城市
作者
Weiwei W. Fang,Xue Feng,Yi Ding,Naixue N. Xiong,Victor C. M. Leung
出处
期刊:IEEE Transactions on Industrial Informatics [Institute of Electrical and Electronics Engineers]
卷期号:17 (9): 6144-6152 被引量:42
标识
DOI:10.1109/tii.2020.3044930
摘要

Motivated by the prospects of 5G communications and industrial Internet of Things (IoT), recent years have seen the rise of a new computing paradigm, edge computing, which shifts data analytics to network edges that are at the proximity of big data sources. Although deep neural networks (DNNs) have been extensively used in many platforms and scenarios, they are usually both compute and memory intensive, thus, difficult to be deployed on resource-limited edge devices and in performance-demanding edge applications. Hence, there is an urgent need for techniques that enable DNN models to fit into edge devices, while ensuring acceptable execution costs and inference accuracy. This article proposes an on-demand DNN model inference system for industrial edge devices, called knowledge distillation and early exit on edge (EdgeKE). It focuses on the following two design knobs: first, DNN compression based on knowledge distillation, which trains the compact edge models under the supervision of large complex models for improving accuracy and speed; second, DNN acceleration based on early exit, which provides flexible choices for satisfying distinct latency or accuracy requirements from edge applications. By extensive evaluations on the CIFAR100 dataset and across three state-of-art edge devices, experimental results demonstrate that EdgeKE significantly outperforms the baseline models in terms of inference latency and memory footprint, while maintaining competitive classification accuracy. Furthermore, EdgeKE is verified to be efficiently adaptive to the application requirements on the inference performance. The accuracy loss is within 4.84% under various latency constraints, and the speedup ratio is up to 3.30× under various accuracy requirements.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
我是老大的应助被gfhdf采纳,获得10
刚刚
fantasy的应助被gfhdf采纳,获得10
刚刚
CarryLJR的应助被gfhdf采纳,获得10
1秒前
WH完成签到,获得积分10
1秒前
DD关闭了DD的文献求助
1秒前
情怀的应助被gfhdf采纳,获得10
1秒前
1秒前
笑点低立辉完成签到,获得积分10
1秒前
知之发布了新的文献求助10
1秒前
yy家的小哥哥完成签到,获得积分10
2秒前
姜贵雨发布了新的文献求助10
2秒前
仁爱觅风发布了新的文献求助20
2秒前
深情安青的应助被许瑞琳采纳,获得10
3秒前
111111完成签到,获得积分10
3秒前
zzzzzzzzzzz完成签到,获得积分10
4秒前
4秒前
水煮电吹风的应助被冲冲冲采纳,获得10
4秒前
4秒前
4秒前
英姑的应助被落雁长歌采纳,获得10
4秒前
科目三的应助被迷人映天采纳,获得10
4秒前
cy完成签到,获得积分10
4秒前
lei完成签到,获得积分10
4秒前
科岚完成签到 ,获得积分10
5秒前
wqh796完成签到,获得积分10
5秒前
悠游书浪完成签到,获得积分10
5秒前
6秒前
oooh发布了新的文献求助10
6秒前
6秒前
丘比特的应助被e00ec采纳,获得10
6秒前
强健的碧琴完成签到,获得积分10
7秒前
红枣完成签到,获得积分10
7秒前
7秒前
7秒前
Lyufang完成签到,获得积分10
7秒前
南风吹梦完成签到,获得积分10
7秒前
怕孤单的嚣完成签到,获得积分10
8秒前
8秒前
8秒前
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180927
求助须知:如何正确求助?哪些是违规求助? 9570973
关于积分的说明 21815578
捐赠科研通 7777227
什么是DOI,文献DOI怎么找? 3433367
关于科研通互助平台的介绍 2557621
邀请新用户注册赠送积分活动 2479346