Learning-Based Edge-Device Collaborative DNN Inference in IoVT Networks

计算机科学 推论 GSM演进的增强数据速率 边缘设备 人工智能 机器学习 计算机网络 操作系统 云计算
作者
Xiaodong Xu,Kaiwen Yan,Shujun Han,Bizhu Wang,Xiaofeng Tao,Ping Zhang
出处
期刊:IEEE Internet of Things Journal [Institute of Electrical and Electronics Engineers]
卷期号:11 (5): 7989-8004 被引量:6
标识
DOI:10.1109/jiot.2023.3317785
摘要

Deep neural network (DNN) is a promising technology for Internet of Visual Things (IoVT) devices to extrct their visual information from unstructured data. However, it is hard to deploy a complete DNN model at resource-constrained IoVT devices to fulfill their latency, energy, and inference accuracy demands. Exploiting the reachable and available computing resources of IoVT devices and mobile-edge computing (MEC) servers, we propose an edge-device collaborative DNN inference framework to empower resource-constrained IoVT devices to perform DNN-based inference. Especially, the DNN model partition separates the DNN model into two parts, which are deployed on both the IoVT devices and multiaccess MEC server for performing inference collaboratively. The DNN early exit and computation resource allocation are employed to accelerate the DNN inference while guaranteeing the inference accuracy. Moreover, a metric to measure the inference performance of average latency and accuracy (IPLA) is designed. Joint multiuser DNN partitioning, early exit point selection, and computation resource allocation are optimized to maximize the tradeoff performance of inference latency and accuracy. We model the optimized problem as an Markov decision process and propose a deep deterministic policy gradient-based edge-device collaborative DNN inference algorithm to solve the problem of huge state space and high-dimensional continuous actions. Experiments are conducted with the Alexnet model on the data set of CIFAR-10 and Resnet-50 model on the data set of ImageNet. Simulation results verify that the proposed algorithm speeds up the overall inference execution of IoVT devices while guaranteeing inference accuracy.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
3秒前
4秒前
bzdjsmw完成签到 ,获得积分10
4秒前
WebCasa应助旦皋采纳,获得10
4秒前
路易斯完成签到,获得积分10
5秒前
颜愫发布了新的文献求助10
5秒前
萌萌完成签到,获得积分10
6秒前
研友_X89o6n完成签到,获得积分10
8秒前
Ther发布了新的文献求助10
10秒前
哈哈哈完成签到,获得积分10
11秒前
13秒前
诚心的初露完成签到,获得积分10
13秒前
lyb完成签到 ,获得积分10
15秒前
风中方盒完成签到,获得积分20
15秒前
布丁圆团完成签到,获得积分10
16秒前
yikeshu完成签到,获得积分10
16秒前
Zoe完成签到 ,获得积分10
17秒前
19秒前
星辰大海应助do0采纳,获得10
20秒前
tt完成签到 ,获得积分10
21秒前
浅辰完成签到,获得积分10
22秒前
大气萤完成签到,获得积分20
23秒前
23秒前
我ppp完成签到 ,获得积分10
23秒前
24秒前
易燃物品完成签到,获得积分10
24秒前
Hello应助Ther采纳,获得10
26秒前
CherylZhao完成签到,获得积分10
27秒前
Galato发布了新的文献求助10
28秒前
颜愫完成签到,获得积分10
28秒前
安详向日葵完成签到 ,获得积分10
29秒前
拼搏的白云完成签到,获得积分10
29秒前
852应助hhh采纳,获得10
29秒前
李白白白完成签到,获得积分10
29秒前
王手完成签到,获得积分10
29秒前
30秒前
一人完成签到,获得积分10
31秒前
do0完成签到,获得积分10
32秒前
yar应助xlz110采纳,获得10
32秒前
NexusExplorer应助落寞凌波采纳,获得10
34秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038368
求助须知:如何正确求助?哪些是违规求助? 3576068
关于积分的说明 11374313
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029