Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges

With the rapid development of mobile communication technologies and Internet of Things (IoT) devices, Multi-Access Edge Computing (MEC) has become one of the most potential technologies for wireless communication. In MEC systems, faster and more reliable data processing can be provided to IoT device...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongqiang Luo, Xiang Dai
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016824007798
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846160431458025472
author Zhongqiang Luo
Xiang Dai
author_facet Zhongqiang Luo
Xiang Dai
author_sort Zhongqiang Luo
collection DOAJ
description With the rapid development of mobile communication technologies and Internet of Things (IoT) devices, Multi-Access Edge Computing (MEC) has become one of the most potential technologies for wireless communication. In MEC systems, faster and more reliable data processing can be provided to IoT devices through computation offloading, but edge servers have limited computing and storage resources. The prerequisite for whether an IoT device can offload a computation task to an edge server for processing is whether the edge server has enough remaining available resources and whether the edge server caches the services related to the task, followed by finding the best way to offload the task. Therefore, to process tasks efficiently, offloading decisions, resource allocation, and edge caching need to be jointly considered during offloading tasks to edge servers. Reinforcement Learning (RL) has recently emerged as a key technique for solving the computation offloading problem in MEC, and a large number of optimization methods have emerged. In this context, we provide a comprehensive survey of RL-based computation offloading fundamental principles and theories in MEC, including mechanisms for finding optimal offloading decisions, methods for joint resource allocation, and means for joint edge caching. In addition, we also discuss the challenges and future work of RL-based computation offloading methods.
format Article
id doaj-art-d194fc3de77b4f0c9b69835fc5712084
institution Kabale University
issn 1110-0168
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Alexandria Engineering Journal
spelling doaj-art-d194fc3de77b4f0c9b69835fc57120842024-11-22T07:36:09ZengElsevierAlexandria Engineering Journal1110-01682024-12-0110889107Reinforcement learning-based computation offloading in edge computing: Principles, methods, challengesZhongqiang Luo0Xiang Dai1School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, 644000, Sichuan, China; Artificial Intelligence Key Laboratory of Sichuan Province, Sichuan University of Science & Engineering, Yibin, 644000, Sichuan, China; Corresponding author.School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, 644000, Sichuan, ChinaWith the rapid development of mobile communication technologies and Internet of Things (IoT) devices, Multi-Access Edge Computing (MEC) has become one of the most potential technologies for wireless communication. In MEC systems, faster and more reliable data processing can be provided to IoT devices through computation offloading, but edge servers have limited computing and storage resources. The prerequisite for whether an IoT device can offload a computation task to an edge server for processing is whether the edge server has enough remaining available resources and whether the edge server caches the services related to the task, followed by finding the best way to offload the task. Therefore, to process tasks efficiently, offloading decisions, resource allocation, and edge caching need to be jointly considered during offloading tasks to edge servers. Reinforcement Learning (RL) has recently emerged as a key technique for solving the computation offloading problem in MEC, and a large number of optimization methods have emerged. In this context, we provide a comprehensive survey of RL-based computation offloading fundamental principles and theories in MEC, including mechanisms for finding optimal offloading decisions, methods for joint resource allocation, and means for joint edge caching. In addition, we also discuss the challenges and future work of RL-based computation offloading methods.http://www.sciencedirect.com/science/article/pii/S1110016824007798Edge computingReinforcement learningComputation offloadingOffloading decisionEdge cachingResource allocation
spellingShingle Zhongqiang Luo
Xiang Dai
Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges
Alexandria Engineering Journal
Edge computing
Reinforcement learning
Computation offloading
Offloading decision
Edge caching
Resource allocation
title Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges
title_full Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges
title_fullStr Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges
title_full_unstemmed Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges
title_short Reinforcement learning-based computation offloading in edge computing: Principles, methods, challenges
title_sort reinforcement learning based computation offloading in edge computing principles methods challenges
topic Edge computing
Reinforcement learning
Computation offloading
Offloading decision
Edge caching
Resource allocation
url http://www.sciencedirect.com/science/article/pii/S1110016824007798
work_keys_str_mv AT zhongqiangluo reinforcementlearningbasedcomputationoffloadinginedgecomputingprinciplesmethodschallenges
AT xiangdai reinforcementlearningbasedcomputationoffloadinginedgecomputingprinciplesmethodschallenges