Deep learning-based computation offloading with energy and performance optimization
Abstract With the benefit of partially or entirely offloading computations to a nearby server, mobile edge computing gives user equipment (UE) more powerful capability to run computationally intensive applications. However, a critical challenge emerged: how to select the optimal set of components to...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2020-03-01
|
Series: | EURASIP Journal on Wireless Communications and Networking |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13638-020-01678-5 |
id |
doaj-bb05a0510bf343d4ae11ca483173526f |
---|---|
record_format |
Article |
spelling |
doaj-bb05a0510bf343d4ae11ca483173526f2020-11-25T02:07:02ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992020-03-01202011810.1186/s13638-020-01678-5Deep learning-based computation offloading with energy and performance optimizationYongsheng Gong0Congmin Lv1Suzhi Cao2Lei Yan3Houpeng Wang4Technology and Engineering Center for Space Utilization, Chinese Academy of SciencesTechnology and Engineering Center for Space Utilization, Chinese Academy of SciencesTechnology and Engineering Center for Space Utilization, Chinese Academy of SciencesTechnology and Engineering Center for Space Utilization, Chinese Academy of SciencesTechnology and Engineering Center for Space Utilization, Chinese Academy of SciencesAbstract With the benefit of partially or entirely offloading computations to a nearby server, mobile edge computing gives user equipment (UE) more powerful capability to run computationally intensive applications. However, a critical challenge emerged: how to select the optimal set of components to offload considering the UE performance as well as its battery usage constraints. In this paper, we propose a novel energy and performance efficient deep learning based offloading algorithm. The optimal offloading schemes of components based on remaining energy and its performance can be determined by our proposed algorithm. All of these considerations are modeled as a cost function; then, a deep learning network is trained to compute the solution by which the optimal offloading scheme can be determined. Experimental results show that the proposed method is superior to existing methods in terms of energy and performance constraints.http://link.springer.com/article/10.1186/s13638-020-01678-5Computation offloadingDeep learningMobile edge computingEnergy and performance optimization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yongsheng Gong Congmin Lv Suzhi Cao Lei Yan Houpeng Wang |
spellingShingle |
Yongsheng Gong Congmin Lv Suzhi Cao Lei Yan Houpeng Wang Deep learning-based computation offloading with energy and performance optimization EURASIP Journal on Wireless Communications and Networking Computation offloading Deep learning Mobile edge computing Energy and performance optimization |
author_facet |
Yongsheng Gong Congmin Lv Suzhi Cao Lei Yan Houpeng Wang |
author_sort |
Yongsheng Gong |
title |
Deep learning-based computation offloading with energy and performance optimization |
title_short |
Deep learning-based computation offloading with energy and performance optimization |
title_full |
Deep learning-based computation offloading with energy and performance optimization |
title_fullStr |
Deep learning-based computation offloading with energy and performance optimization |
title_full_unstemmed |
Deep learning-based computation offloading with energy and performance optimization |
title_sort |
deep learning-based computation offloading with energy and performance optimization |
publisher |
SpringerOpen |
series |
EURASIP Journal on Wireless Communications and Networking |
issn |
1687-1499 |
publishDate |
2020-03-01 |
description |
Abstract With the benefit of partially or entirely offloading computations to a nearby server, mobile edge computing gives user equipment (UE) more powerful capability to run computationally intensive applications. However, a critical challenge emerged: how to select the optimal set of components to offload considering the UE performance as well as its battery usage constraints. In this paper, we propose a novel energy and performance efficient deep learning based offloading algorithm. The optimal offloading schemes of components based on remaining energy and its performance can be determined by our proposed algorithm. All of these considerations are modeled as a cost function; then, a deep learning network is trained to compute the solution by which the optimal offloading scheme can be determined. Experimental results show that the proposed method is superior to existing methods in terms of energy and performance constraints. |
topic |
Computation offloading Deep learning Mobile edge computing Energy and performance optimization |
url |
http://link.springer.com/article/10.1186/s13638-020-01678-5 |
work_keys_str_mv |
AT yongshenggong deeplearningbasedcomputationoffloadingwithenergyandperformanceoptimization AT congminlv deeplearningbasedcomputationoffloadingwithenergyandperformanceoptimization AT suzhicao deeplearningbasedcomputationoffloadingwithenergyandperformanceoptimization AT leiyan deeplearningbasedcomputationoffloadingwithenergyandperformanceoptimization AT houpengwang deeplearningbasedcomputationoffloadingwithenergyandperformanceoptimization |
_version_ |
1724931608355536896 |