Low Latency Deep Learning Inference Model for Distributed Intelligent IoT Edge Clusters

作者
Soumyalatha Naveen,Manjunath R Kounte,Mohammed Riyaz Ahmed
出处
期刊:IEEE Access [Institute of Electrical and Electronics Engineers]
卷期号:9: 160607-160621 被引量:54
标识
DOI:10.1109/access.2021.3131396
摘要

Edge computing is a new paradigm enabling intelligent applications for the Internet of Things (IoT) using mobile, low-cost IoT devices embedded with data analytics. Due to the resource limitations of Internet of Things devices, it is essential to use these resources optimally. Therefore, intelligence needs to be applied through an efficient deep learning model to optimize resources like memory, power, and computational ability. In addition, intelligent edge computing is essential for real-time applications requiring end-to-end delay or response time within a few seconds. We propose decentralized heterogeneous edge clusters deployed with an optimized pre-trained yolov2 model. In our model, the weights have been pruned and then split into fused layers and distributed to edge devices for processing. Later the gateway device merges the partial results from each edge device to obtain the processed output. We deploy a convolutional neural network (CNN) on resource-constraint IoT devices to make them intelligent and realistic. Evaluation was done by deploying the proposed model on five IoT edge devices and a gateway device enabled with hardware accelerator. The evaluation of our proposed model shows significant improvement in terms of communication size and inference latency. Compared to DeepThings for 5 X 5 fused layer partitioning for five devices, our proposed model reduces communication size by ~ 14.4% and inference latency by ~16%.

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
pokiy完成签到,获得积分10
刚刚
刚刚
yulong发布了新的文献求助10
刚刚
meredith完成签到,获得积分10
刚刚
我爱科研发布了新的文献求助10
1秒前
自由的寒蕾完成签到,获得积分10
1秒前
欢喜的半鬼完成签到 ,获得积分10
1秒前
xshzhou完成签到,获得积分10
1秒前
1秒前
1秒前
lili完成签到,获得积分10
1秒前
安彤完成签到 ,获得积分10
1秒前
1秒前
2秒前
落雁长歌发布了新的文献求助10
2秒前
lirui_nicely完成签到,获得积分10
2秒前
2秒前
3秒前
啾啾啾完成签到,获得积分10
3秒前
sound发布了新的文献求助10
4秒前
jingdou完成签到,获得积分10
4秒前
2puerile完成签到,获得积分10
4秒前
hhh完成签到,获得积分10
4秒前
4秒前
why发布了新的文献求助10
4秒前
zk092988完成签到,获得积分10
5秒前
5秒前
5秒前
思源的应助被puff采纳,获得10
6秒前
活力川发布了新的文献求助10
6秒前
llllx完成签到,获得积分10
6秒前
pukej完成签到 ,获得积分10
7秒前
蘑菇发布了新的文献求助10
7秒前
null的应助被苦瓜采纳,获得10
7秒前
7秒前
深情安青的应助被儒雅的巧曼采纳,获得10
7秒前
科研通AI6.2的应助被主将从现采纳,获得10
7秒前
生活顺利发布了新的文献求助10
7秒前
7秒前
lili发布了新的文献求助10
8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