SFL-TUM:用于无人机辅助 MEC 网络中大规模人工智能模型任务卸载的高能效 SFRL 方法

IF 5.8 2区 计算机科学 Q1 TELECOMMUNICATIONS
Prakhar Consul , Ishan Budhiraja , Deepak Garg , Sahil Garg , Georges Kaddoum , Mohammad Mehedi Hassan
{"title":"SFL-TUM:用于无人机辅助 MEC 网络中大规模人工智能模型任务卸载的高能效 SFRL 方法","authors":"Prakhar Consul ,&nbsp;Ishan Budhiraja ,&nbsp;Deepak Garg ,&nbsp;Sahil Garg ,&nbsp;Georges Kaddoum ,&nbsp;Mohammad Mehedi Hassan","doi":"10.1016/j.vehcom.2024.100790","DOIUrl":null,"url":null,"abstract":"<div><p>The convergence of mobile edge computing (MEC) network with unmanned aerial vehicles (UAVs) presents an auspicious opportunity to revolutionize wireless communication and facilitate high-speed internet access in remote regions for mobile devices (MDs) as well as large scale artificial intelligence (AI) models. However, the substantial amount of data produced by the UAVs-assisted MEC network necessitates the integration of efficient distributed learning techniques in AI models. In recent times, distributed learning algorithms, including federated reinforcement learning (FRL) and split learning (SL), have been explored for the purpose of learning machine learning (ML) models that are distributed by sharing model parameters, as opposed to large raw data-sets as seen in traditional centralized learning algorithms. To implement the hybrid method, the model is first trained locally on each UAV-assisted MEC network using SL. Subsequently, the model parameters that have been encrypted are sent to a central server for federated averaging. Finally, after the model has been updated, it is distributed to each UAV-assisted MEC network for local fine-tuning. Our simulations indicate that the proposed split and federated reinforcement learning (SFRL) framework yields comparable high-test accuracy performance while consuming less energy compared to extant distributed learning algorithms. Furthermore, the SFRL algorithm efficiently realizes energy-efficient selection between the SL and FRL methods under different distributions. Numerical results shows that the proposed scheme improves the accuracy by 29.31% and reduced the energy consumption by around 67.34% and time delay by about 7.37%. as compared to the existing baseline schemes.</p></div>","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":null,"pages":null},"PeriodicalIF":5.8000,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"SFL-TUM: Energy efficient SFRL method for large scale AI model's task offloading in UAV-assisted MEC networks\",\"authors\":\"Prakhar Consul ,&nbsp;Ishan Budhiraja ,&nbsp;Deepak Garg ,&nbsp;Sahil Garg ,&nbsp;Georges Kaddoum ,&nbsp;Mohammad Mehedi Hassan\",\"doi\":\"10.1016/j.vehcom.2024.100790\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The convergence of mobile edge computing (MEC) network with unmanned aerial vehicles (UAVs) presents an auspicious opportunity to revolutionize wireless communication and facilitate high-speed internet access in remote regions for mobile devices (MDs) as well as large scale artificial intelligence (AI) models. However, the substantial amount of data produced by the UAVs-assisted MEC network necessitates the integration of efficient distributed learning techniques in AI models. In recent times, distributed learning algorithms, including federated reinforcement learning (FRL) and split learning (SL), have been explored for the purpose of learning machine learning (ML) models that are distributed by sharing model parameters, as opposed to large raw data-sets as seen in traditional centralized learning algorithms. To implement the hybrid method, the model is first trained locally on each UAV-assisted MEC network using SL. Subsequently, the model parameters that have been encrypted are sent to a central server for federated averaging. Finally, after the model has been updated, it is distributed to each UAV-assisted MEC network for local fine-tuning. Our simulations indicate that the proposed split and federated reinforcement learning (SFRL) framework yields comparable high-test accuracy performance while consuming less energy compared to extant distributed learning algorithms. Furthermore, the SFRL algorithm efficiently realizes energy-efficient selection between the SL and FRL methods under different distributions. Numerical results shows that the proposed scheme improves the accuracy by 29.31% and reduced the energy consumption by around 67.34% and time delay by about 7.37%. as compared to the existing baseline schemes.</p></div>\",\"PeriodicalId\":54346,\"journal\":{\"name\":\"Vehicular Communications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.8000,\"publicationDate\":\"2024-05-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Vehicular Communications\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2214209624000652\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"TELECOMMUNICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Vehicular Communications","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214209624000652","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

移动边缘计算(MEC)网络与无人飞行器(UAV)的融合为无线通信带来了革命性的机遇,促进了偏远地区移动设备(MD)和大型人工智能(AI)模型的高速互联网接入。然而,无人机辅助 MEC 网络产生的大量数据要求在人工智能模型中集成高效的分布式学习技术。近来,人们探索了分布式学习算法,包括联合强化学习(FRL)和分裂学习(SL),用于学习机器学习(ML)模型,这些模型通过共享模型参数进行分布式学习,而非传统集中式学习算法中的大型原始数据集。为了实现混合方法,首先使用 SL 在每个无人机辅助 MEC 网络上对模型进行本地训练。随后,经过加密的模型参数被发送到中央服务器进行联合平均。最后,在模型更新后,将其分发到每个无人机辅助 MEC 网络,进行本地微调。我们的模拟结果表明,与现有的分布式学习算法相比,我们提出的分离式联合强化学习(SFRL)框架在消耗更少能量的同时,还能获得相当高的测试精度。此外,SFRL 算法还能在不同分布条件下有效实现 SL 和 FRL 方法之间的节能选择。数值结果表明,与现有的基线方案相比,所提出的方案提高了 29.31% 的准确率,减少了约 67.34% 的能耗和约 7.37% 的时间延迟。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
SFL-TUM: Energy efficient SFRL method for large scale AI model's task offloading in UAV-assisted MEC networks

The convergence of mobile edge computing (MEC) network with unmanned aerial vehicles (UAVs) presents an auspicious opportunity to revolutionize wireless communication and facilitate high-speed internet access in remote regions for mobile devices (MDs) as well as large scale artificial intelligence (AI) models. However, the substantial amount of data produced by the UAVs-assisted MEC network necessitates the integration of efficient distributed learning techniques in AI models. In recent times, distributed learning algorithms, including federated reinforcement learning (FRL) and split learning (SL), have been explored for the purpose of learning machine learning (ML) models that are distributed by sharing model parameters, as opposed to large raw data-sets as seen in traditional centralized learning algorithms. To implement the hybrid method, the model is first trained locally on each UAV-assisted MEC network using SL. Subsequently, the model parameters that have been encrypted are sent to a central server for federated averaging. Finally, after the model has been updated, it is distributed to each UAV-assisted MEC network for local fine-tuning. Our simulations indicate that the proposed split and federated reinforcement learning (SFRL) framework yields comparable high-test accuracy performance while consuming less energy compared to extant distributed learning algorithms. Furthermore, the SFRL algorithm efficiently realizes energy-efficient selection between the SL and FRL methods under different distributions. Numerical results shows that the proposed scheme improves the accuracy by 29.31% and reduced the energy consumption by around 67.34% and time delay by about 7.37%. as compared to the existing baseline schemes.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Vehicular Communications
Vehicular Communications Engineering-Electrical and Electronic Engineering
CiteScore
12.70
自引率
10.40%
发文量
88
审稿时长
62 days
期刊介绍: Vehicular communications is a growing area of communications between vehicles and including roadside communication infrastructure. Advances in wireless communications are making possible sharing of information through real time communications between vehicles and infrastructure. This has led to applications to increase safety of vehicles and communication between passengers and the Internet. Standardization efforts on vehicular communication are also underway to make vehicular transportation safer, greener and easier. The aim of the journal is to publish high quality peer–reviewed papers in the area of vehicular communications. The scope encompasses all types of communications involving vehicles, including vehicle–to–vehicle and vehicle–to–infrastructure. The scope includes (but not limited to) the following topics related to vehicular communications: Vehicle to vehicle and vehicle to infrastructure communications Channel modelling, modulating and coding Congestion Control and scalability issues Protocol design, testing and verification Routing in vehicular networks Security issues and countermeasures Deployment and field testing Reducing energy consumption and enhancing safety of vehicles Wireless in–car networks Data collection and dissemination methods Mobility and handover issues Safety and driver assistance applications UAV Underwater communications Autonomous cooperative driving Social networks Internet of vehicles Standardization of protocols.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信