Offloading in V2X with road side units: Deep reinforcement learning

IF 5.8 2区 计算机科学 Q1 TELECOMMUNICATIONS Vehicular Communications Pub Date : 2024-12-05 DOI:10.1016/j.vehcom.2024.100862
Widhi Yahya, Ying-Dar Lin, Faysal Marzuk, Piotr Chołda, Yuan-Cheng Lai
{"title":"Offloading in V2X with road side units: Deep reinforcement learning","authors":"Widhi Yahya, Ying-Dar Lin, Faysal Marzuk, Piotr Chołda, Yuan-Cheng Lai","doi":"10.1016/j.vehcom.2024.100862","DOIUrl":null,"url":null,"abstract":"Traffic offloading is crucial for reducing computing latency in distributed edge systems such as vehicle-to-everything (V2X) networks, which use roadside units (RSUs) and access network mobile edge computing (AN-MEC) with ML agents. Traffic offloading is part of the control plane problem, which requires fast decision-making in complex V2X systems. This study presents a novel ratio-based offloading strategy using the twin delayed deep deterministic policy gradient (TD3) algorithm to optimize offloading ratios in a two-tier V2X system, enabling computation at both RSUs and the edge. The offloading optimization covers both vertical and horizontal offloading, introducing a continuous search space that needs fast decision-making to accommodate fluctuating traffic in complex V2X systems. We developed a V2X environment to evaluate the performance of the offloading agent, incorporating latency models, state and action definitions, and reward structures. A comparative analysis with metaheuristic simulated annealing (SA) is conducted, and the impact of single versus multiple offloading agents with deployment options at a centralized central office (CO) is examined. Evaluation results indicate that TD3's decision time is five orders of magnitude faster than SA. For 10 and 50 sites, SA takes 602 and 20,421 seconds, respectively, while single-agent TD3 requires 4 to 24 milliseconds and multi-agent TD3 takes 1 to 3 milliseconds. The average latency for SA ranges from 0.18 to 0.32 milliseconds, single-agent TD3 from 0.26 to 0.5 milliseconds, and multi-agent TD3 from 0.22 to 0.45 milliseconds, demonstrating that TD3 approximates SA performance with initial training.","PeriodicalId":54346,"journal":{"name":"Vehicular Communications","volume":"29 1","pages":""},"PeriodicalIF":5.8000,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Vehicular Communications","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1016/j.vehcom.2024.100862","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

Abstract

Traffic offloading is crucial for reducing computing latency in distributed edge systems such as vehicle-to-everything (V2X) networks, which use roadside units (RSUs) and access network mobile edge computing (AN-MEC) with ML agents. Traffic offloading is part of the control plane problem, which requires fast decision-making in complex V2X systems. This study presents a novel ratio-based offloading strategy using the twin delayed deep deterministic policy gradient (TD3) algorithm to optimize offloading ratios in a two-tier V2X system, enabling computation at both RSUs and the edge. The offloading optimization covers both vertical and horizontal offloading, introducing a continuous search space that needs fast decision-making to accommodate fluctuating traffic in complex V2X systems. We developed a V2X environment to evaluate the performance of the offloading agent, incorporating latency models, state and action definitions, and reward structures. A comparative analysis with metaheuristic simulated annealing (SA) is conducted, and the impact of single versus multiple offloading agents with deployment options at a centralized central office (CO) is examined. Evaluation results indicate that TD3's decision time is five orders of magnitude faster than SA. For 10 and 50 sites, SA takes 602 and 20,421 seconds, respectively, while single-agent TD3 requires 4 to 24 milliseconds and multi-agent TD3 takes 1 to 3 milliseconds. The average latency for SA ranges from 0.18 to 0.32 milliseconds, single-agent TD3 from 0.26 to 0.5 milliseconds, and multi-agent TD3 from 0.22 to 0.45 milliseconds, demonstrating that TD3 approximates SA performance with initial training.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
在 V2X 中使用路侧装置进行卸载:深度强化学习
流量卸载对于减少分布式边缘系统(如车对万物(V2X)网络)中的计算延迟至关重要,这些系统使用路边装置(RSU)和带有 ML 代理的接入网移动边缘计算(AN-MEC)。流量卸载是控制平面问题的一部分,需要在复杂的 V2X 系统中快速做出决策。本研究提出了一种基于比率的新型卸载策略,使用双延迟深度确定性策略梯度(TD3)算法来优化双层 V2X 系统中的卸载比率,使 RSU 和边缘计算成为可能。卸载优化涵盖垂直和水平卸载,引入了一个连续的搜索空间,需要快速决策以适应复杂 V2X 系统中波动的流量。我们开发了一个 V2X 环境来评估卸载代理的性能,其中包括延迟模型、状态和行动定义以及奖励结构。我们进行了元启发式模拟退火(SA)比较分析,并研究了在集中式中央办公室(CO)部署单个卸载代理与多个卸载代理的影响。评估结果表明,TD3 的决策时间比 SA 快五个数量级。对于 10 个和 50 个站点,SA 分别需要 602 秒和 20,421 秒,而单代理 TD3 需要 4 到 24 毫秒,多代理 TD3 需要 1 到 3 毫秒。SA 的平均延迟时间为 0.18 到 0.32 毫秒,单个代理 TD3 为 0.26 到 0.5 毫秒,而多代理 TD3 为 0.22 到 0.45 毫秒,这表明 TD3 经过初步训练后性能接近 SA。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 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.
期刊最新文献
RIS-aided jellyfish search optimization for multiuser wireless networks improvement A review of smart vehicles in smart cities: Dangers, impacts, and the threat landscape Federated learning on the go: Building stable clusters and optimizing resources on the road VeTraSPM: Novel vehicle trajectory data sequential pattern mining algorithm for link criticality analysis The stability for CACC system with time delays and reconstitution information of vehicles for compensating delays based on Bi-LSTM
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1