期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 18, 期 4, 页码 2820-2829出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2021.3075464
关键词
Computational modeling; Object oriented modeling; Cloud computing; Servers; Neural networks; Informatics; Estimation; Computation offloading; deep neural networks (DNNs); intelligent Internet of Things (IoT) application; mobile edge computing (MEC); software adaption
类别
资金
- National Natural Science Foundation of China [62072108]
- Natural Science Foundation of Fujian Province for Distinguished Young Scholars [2020J06014]
This article introduces a solution for running DNN-based applications on intelligent devices with limited resources, employing computation offloading technology to transfer some computation-intensive tasks to the cloud or edges. By rewriting the source code and dynamically determining the offloading scheme, this solution demonstrates significant performance advantages on a real-world intelligent application.
A deep neural network (DNN) has become increasingly popular in industrial Internet of Things scenarios. Due to high demands on computational capability, it is hard for DNN-based applications to directly run on intelligent end devices with limited resources. Computation offloading technology offers a feasible solution by offloading some computation-intensive tasks to the cloud or edges. Supporting such capability is not easy due to two aspects: Adaptability: offloading should dynamically occur among computation nodes. Effectiveness: it needs to be determined which parts are worth offloading. This article proposes a novel approach, called DNNOff. For a given DNN-based application, DNNOff first rewrites the source code to implement a special program structure supporting on-demand offloading and, at runtime, automatically determines the offloading scheme. We evaluated DNNOff on a real-world intelligent application, with three DNN models. Our results show that, compared with other approaches, DNNOff saves response time by 12.4-66.6% on average.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据