Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge Computing
Due to the high demands of deep neural network (DNN) based applications on computational capability, it is hard for them to be directly run on mobile devices with limited resources. Computation offloading technology offers a feasible solution by offloading some computation-intensive tasks of neural...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9123407/ |
id |
doaj-0e9440e0f9714778bbcbf5bbc55388bc |
---|---|
record_format |
Article |
spelling |
doaj-0e9440e0f9714778bbcbf5bbc55388bc2021-03-30T02:27:40ZengIEEEIEEE Access2169-35362020-01-01811553711554710.1109/ACCESS.2020.30045099123407Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge ComputingZheyi Chen0https://orcid.org/0000-0002-6349-068XJunqin Hu1Xing Chen2Jia Hu3https://orcid.org/0000-0001-5406-8420Xianghan Zheng4Geyong Min5https://orcid.org/0000-0003-1395-7314College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K.College of Mathematics and Computer Science, Fuzhou University, Fuzhou, ChinaCollege of Mathematics and Computer Science, Fuzhou University, Fuzhou, ChinaCollege of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K.College of Mathematics and Computer Science, Fuzhou University, Fuzhou, ChinaCollege of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K.Due to the high demands of deep neural network (DNN) based applications on computational capability, it is hard for them to be directly run on mobile devices with limited resources. Computation offloading technology offers a feasible solution by offloading some computation-intensive tasks of neural network layers to edges or remote clouds that are equipped with sufficient resources. However, the offloading process might lead to excessive delays and thus seriously affect the user experience. To address this important problem, we first regard the average response time of multi-task parallel scheduling as our optimization goal. Next, the problem of computation offloading and task scheduling for DNN-based applications in cloud-edge computing is formulated with a scheme evaluation algorithm. Finally, the greedy and genetic algorithms based methods are proposed to solve the problem. The extensive experiments are conducted to demonstrate the effectiveness of the proposed methods for scheduling tasks of DNN-based applications in different cloud-edge environments. The results show that the proposed methods can obtain the near-optimal scheduling performance, and generate less average response time than traditional scheduling schemes. Moreover, the genetic algorithm leads to less average response time than the greedy algorithm, but the genetic algorithm needs more running time.https://ieeexplore.ieee.org/document/9123407/Cloud-edge computingDNN-based applicationscomputation offloadingtask schedulinggreedy algorithmgenetic algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zheyi Chen Junqin Hu Xing Chen Jia Hu Xianghan Zheng Geyong Min |
spellingShingle |
Zheyi Chen Junqin Hu Xing Chen Jia Hu Xianghan Zheng Geyong Min Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge Computing IEEE Access Cloud-edge computing DNN-based applications computation offloading task scheduling greedy algorithm genetic algorithm |
author_facet |
Zheyi Chen Junqin Hu Xing Chen Jia Hu Xianghan Zheng Geyong Min |
author_sort |
Zheyi Chen |
title |
Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge Computing |
title_short |
Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge Computing |
title_full |
Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge Computing |
title_fullStr |
Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge Computing |
title_full_unstemmed |
Computation Offloading and Task Scheduling for DNN-Based Applications in Cloud-Edge Computing |
title_sort |
computation offloading and task scheduling for dnn-based applications in cloud-edge computing |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Due to the high demands of deep neural network (DNN) based applications on computational capability, it is hard for them to be directly run on mobile devices with limited resources. Computation offloading technology offers a feasible solution by offloading some computation-intensive tasks of neural network layers to edges or remote clouds that are equipped with sufficient resources. However, the offloading process might lead to excessive delays and thus seriously affect the user experience. To address this important problem, we first regard the average response time of multi-task parallel scheduling as our optimization goal. Next, the problem of computation offloading and task scheduling for DNN-based applications in cloud-edge computing is formulated with a scheme evaluation algorithm. Finally, the greedy and genetic algorithms based methods are proposed to solve the problem. The extensive experiments are conducted to demonstrate the effectiveness of the proposed methods for scheduling tasks of DNN-based applications in different cloud-edge environments. The results show that the proposed methods can obtain the near-optimal scheduling performance, and generate less average response time than traditional scheduling schemes. Moreover, the genetic algorithm leads to less average response time than the greedy algorithm, but the genetic algorithm needs more running time. |
topic |
Cloud-edge computing DNN-based applications computation offloading task scheduling greedy algorithm genetic algorithm |
url |
https://ieeexplore.ieee.org/document/9123407/ |
work_keys_str_mv |
AT zheyichen computationoffloadingandtaskschedulingfordnnbasedapplicationsincloudedgecomputing AT junqinhu computationoffloadingandtaskschedulingfordnnbasedapplicationsincloudedgecomputing AT xingchen computationoffloadingandtaskschedulingfordnnbasedapplicationsincloudedgecomputing AT jiahu computationoffloadingandtaskschedulingfordnnbasedapplicationsincloudedgecomputing AT xianghanzheng computationoffloadingandtaskschedulingfordnnbasedapplicationsincloudedgecomputing AT geyongmin computationoffloadingandtaskschedulingfordnnbasedapplicationsincloudedgecomputing |
_version_ |
1724185036832374784 |