Online learning offloading framework for heterogeneous mobile edge computing system

Feifei Zhang, Jidong Ge, Chifong Wong, Chuanyi Li, Xingguo Chen, Sheng Zhang, Bin Luo, He Zhang, Victor Chang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Cloud of Things (CoT) is a significant paradigm for bridging cloud resource and mobile terminals. Mobile edge computing (MEC) is a supporting architecture for CoT. The objectives of this paper are to describe and evaluate a method to handle the computation offloading problem during user mobility which minimizes the offloading failure rate in heterogeneous network. Furthermore, users’ mobility and their choices for offloading lead to the everchanging condition of wireless network and opportunistic resource available. By modeling such dynamic mobile edge environment, quantizing the user cost, failure penalty and diversified QoS requirements, computation offloading problem is converted into an online decision-making problem in a stochastic process. We divide the decision-making into two phases: offloading planning phase and offloading running phase. In both phases the learning agent can continuously improve the control policy. We also conduct a failure recovery policy to tackle different types of failure and is included in the decision-making process. The numerical results show that the proposed online learning offloading method for mobile users can derive the optimal offloading scheme compared with the baseline algorithms.

Original languageEnglish
Pages (from-to)167-183
Number of pages17
JournalJournal of Parallel and Distributed Computing
Volume128
Early online date6 Mar 2019
DOIs
Publication statusE-pub ahead of print - 6 Mar 2019

Fingerprint

Online Learning
Decision making
Computing
Decision Making
Thing
Heterogeneous networks
Random processes
Resources
Wireless networks
Heterogeneous Networks
Quality of service
Failure Rate
Dynamic Modeling
Control Policy
Wireless Networks
Divides
Penalty
Stochastic Processes
Planning
Recovery

Cite this

Zhang, Feifei ; Ge, Jidong ; Wong, Chifong ; Li, Chuanyi ; Chen, Xingguo ; Zhang, Sheng ; Luo, Bin ; Zhang, He ; Chang, Victor. / Online learning offloading framework for heterogeneous mobile edge computing system. In: Journal of Parallel and Distributed Computing. 2019 ; Vol. 128. pp. 167-183.
@article{93877cd3d6b14f8a8b9b90d32392980a,
title = "Online learning offloading framework for heterogeneous mobile edge computing system",
abstract = "Cloud of Things (CoT) is a significant paradigm for bridging cloud resource and mobile terminals. Mobile edge computing (MEC) is a supporting architecture for CoT. The objectives of this paper are to describe and evaluate a method to handle the computation offloading problem during user mobility which minimizes the offloading failure rate in heterogeneous network. Furthermore, users’ mobility and their choices for offloading lead to the everchanging condition of wireless network and opportunistic resource available. By modeling such dynamic mobile edge environment, quantizing the user cost, failure penalty and diversified QoS requirements, computation offloading problem is converted into an online decision-making problem in a stochastic process. We divide the decision-making into two phases: offloading planning phase and offloading running phase. In both phases the learning agent can continuously improve the control policy. We also conduct a failure recovery policy to tackle different types of failure and is included in the decision-making process. The numerical results show that the proposed online learning offloading method for mobile users can derive the optimal offloading scheme compared with the baseline algorithms.",
author = "Feifei Zhang and Jidong Ge and Chifong Wong and Chuanyi Li and Xingguo Chen and Sheng Zhang and Bin Luo and He Zhang and Victor Chang",
year = "2019",
month = "3",
day = "6",
doi = "10.1016/j.jpdc.2019.02.003",
language = "English",
volume = "128",
pages = "167--183",
journal = "Journal of Parallel and Distributed Computing",
issn = "0743-7315",
publisher = "Academic Press Inc.",

}

Online learning offloading framework for heterogeneous mobile edge computing system. / Zhang, Feifei; Ge, Jidong; Wong, Chifong; Li, Chuanyi; Chen, Xingguo; Zhang, Sheng; Luo, Bin; Zhang, He; Chang, Victor.

In: Journal of Parallel and Distributed Computing, Vol. 128, 06.03.2019, p. 167-183.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online learning offloading framework for heterogeneous mobile edge computing system

AU - Zhang, Feifei

AU - Ge, Jidong

AU - Wong, Chifong

AU - Li, Chuanyi

AU - Chen, Xingguo

AU - Zhang, Sheng

AU - Luo, Bin

AU - Zhang, He

AU - Chang, Victor

PY - 2019/3/6

Y1 - 2019/3/6

N2 - Cloud of Things (CoT) is a significant paradigm for bridging cloud resource and mobile terminals. Mobile edge computing (MEC) is a supporting architecture for CoT. The objectives of this paper are to describe and evaluate a method to handle the computation offloading problem during user mobility which minimizes the offloading failure rate in heterogeneous network. Furthermore, users’ mobility and their choices for offloading lead to the everchanging condition of wireless network and opportunistic resource available. By modeling such dynamic mobile edge environment, quantizing the user cost, failure penalty and diversified QoS requirements, computation offloading problem is converted into an online decision-making problem in a stochastic process. We divide the decision-making into two phases: offloading planning phase and offloading running phase. In both phases the learning agent can continuously improve the control policy. We also conduct a failure recovery policy to tackle different types of failure and is included in the decision-making process. The numerical results show that the proposed online learning offloading method for mobile users can derive the optimal offloading scheme compared with the baseline algorithms.

AB - Cloud of Things (CoT) is a significant paradigm for bridging cloud resource and mobile terminals. Mobile edge computing (MEC) is a supporting architecture for CoT. The objectives of this paper are to describe and evaluate a method to handle the computation offloading problem during user mobility which minimizes the offloading failure rate in heterogeneous network. Furthermore, users’ mobility and their choices for offloading lead to the everchanging condition of wireless network and opportunistic resource available. By modeling such dynamic mobile edge environment, quantizing the user cost, failure penalty and diversified QoS requirements, computation offloading problem is converted into an online decision-making problem in a stochastic process. We divide the decision-making into two phases: offloading planning phase and offloading running phase. In both phases the learning agent can continuously improve the control policy. We also conduct a failure recovery policy to tackle different types of failure and is included in the decision-making process. The numerical results show that the proposed online learning offloading method for mobile users can derive the optimal offloading scheme compared with the baseline algorithms.

UR - http://www.scopus.com/inward/record.url?scp=85063211650&partnerID=8YFLogxK

U2 - 10.1016/j.jpdc.2019.02.003

DO - 10.1016/j.jpdc.2019.02.003

M3 - Article

AN - SCOPUS:85063211650

VL - 128

SP - 167

EP - 183

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

SN - 0743-7315

ER -