基于深度强化学习的车联网生态驾驶:Web 3.0 技术在交通优化中的应用

IF 6.2 2区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Future Generation Computer Systems-The International Journal of Escience Pub Date : 2024-09-26 DOI:10.1016/j.future.2024.107544
Minghui Ma , Xu Han , Shidong Liang , Yansong Wang , Lan Jiang
{"title":"基于深度强化学习的车联网生态驾驶:Web 3.0 技术在交通优化中的应用","authors":"Minghui Ma ,&nbsp;Xu Han ,&nbsp;Shidong Liang ,&nbsp;Yansong Wang ,&nbsp;Lan Jiang","doi":"10.1016/j.future.2024.107544","DOIUrl":null,"url":null,"abstract":"<div><div>With the fast development of Web3.0 technology, connected vehicles can now handle and communicate data more safely and effectively. When combined with 5G/6G communication technology, these vehicles can optimize emissions in transportation networks to a greater extent. This study proposed an ecologically car-following model from natural driving data by using deep reinforcement learning under the context of the rapid development of Web 3.0 technologies. Firstly, by utilizing naturalistic driving data, an environment for connected vehicle car-following is created. Secondly, this paper uses SAC (Soft Actor-Critic) deep reinforcement learning algorithm and designs novel reward function based on ecological driving principles and car-following characteristics to reduce fuel consumption and emissions while maintaining safe distance with leading vehicle. Subsequently, the established model is tested, and results indicate that model not only performs well in terms of collision occurrences, Time-to-Collision (TTC), and driving comfort on test set but also achieves reduction of 5.50% in fuel consumption and reductions of 15.04%, 5.63%, and 9.60% in pollutant emissions (NOx, CO, and HC) compared to naturalistic manually driven vehicles.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":null,"pages":null},"PeriodicalIF":6.2000,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Connected vehicles ecological driving based on deep reinforce learning: Application of Web 3.0 technologies in traffic optimization\",\"authors\":\"Minghui Ma ,&nbsp;Xu Han ,&nbsp;Shidong Liang ,&nbsp;Yansong Wang ,&nbsp;Lan Jiang\",\"doi\":\"10.1016/j.future.2024.107544\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>With the fast development of Web3.0 technology, connected vehicles can now handle and communicate data more safely and effectively. When combined with 5G/6G communication technology, these vehicles can optimize emissions in transportation networks to a greater extent. This study proposed an ecologically car-following model from natural driving data by using deep reinforcement learning under the context of the rapid development of Web 3.0 technologies. Firstly, by utilizing naturalistic driving data, an environment for connected vehicle car-following is created. Secondly, this paper uses SAC (Soft Actor-Critic) deep reinforcement learning algorithm and designs novel reward function based on ecological driving principles and car-following characteristics to reduce fuel consumption and emissions while maintaining safe distance with leading vehicle. Subsequently, the established model is tested, and results indicate that model not only performs well in terms of collision occurrences, Time-to-Collision (TTC), and driving comfort on test set but also achieves reduction of 5.50% in fuel consumption and reductions of 15.04%, 5.63%, and 9.60% in pollutant emissions (NOx, CO, and HC) compared to naturalistic manually driven vehicles.</div></div>\",\"PeriodicalId\":55132,\"journal\":{\"name\":\"Future Generation Computer Systems-The International Journal of Escience\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.2000,\"publicationDate\":\"2024-09-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Future Generation Computer Systems-The International Journal of Escience\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0167739X24005089\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, THEORY & METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Future Generation Computer Systems-The International Journal of Escience","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167739X24005089","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0

摘要

随着 Web3.0 技术的快速发展,互联车辆现在可以更安全、更有效地处理和交流数据。当与 5G/6G 通信技术相结合时,这些车辆可以在更大程度上优化交通网络中的排放。在 Web 3.0 技术飞速发展的背景下,本研究利用深度强化学习,从自然驾驶数据中提出了一种生态学汽车跟随模型。首先,通过利用自然驾驶数据,创建了车联网汽车跟车环境。其次,本文采用 SAC(Soft Actor-Critic)深度强化学习算法,并根据生态驾驶原则和跟车特性设计了新颖的奖励函数,以降低油耗和排放,同时与前车保持安全距离。随后,对建立的模型进行了测试,结果表明,与自然手动驾驶车辆相比,该模型不仅在碰撞发生率、碰撞时间(TTC)和驾驶舒适性方面表现出色,而且在油耗方面降低了 5.50%,在污染物排放(氮氧化物、一氧化碳和碳氢化合物)方面分别降低了 15.04%、5.63% 和 9.60%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Connected vehicles ecological driving based on deep reinforce learning: Application of Web 3.0 technologies in traffic optimization
With the fast development of Web3.0 technology, connected vehicles can now handle and communicate data more safely and effectively. When combined with 5G/6G communication technology, these vehicles can optimize emissions in transportation networks to a greater extent. This study proposed an ecologically car-following model from natural driving data by using deep reinforcement learning under the context of the rapid development of Web 3.0 technologies. Firstly, by utilizing naturalistic driving data, an environment for connected vehicle car-following is created. Secondly, this paper uses SAC (Soft Actor-Critic) deep reinforcement learning algorithm and designs novel reward function based on ecological driving principles and car-following characteristics to reduce fuel consumption and emissions while maintaining safe distance with leading vehicle. Subsequently, the established model is tested, and results indicate that model not only performs well in terms of collision occurrences, Time-to-Collision (TTC), and driving comfort on test set but also achieves reduction of 5.50% in fuel consumption and reductions of 15.04%, 5.63%, and 9.60% in pollutant emissions (NOx, CO, and HC) compared to naturalistic manually driven vehicles.
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
CiteScore
19.90
自引率
2.70%
发文量
376
审稿时长
10.6 months
期刊介绍: Computing infrastructures and systems are constantly evolving, resulting in increasingly complex and collaborative scientific applications. To cope with these advancements, there is a growing need for collaborative tools that can effectively map, control, and execute these applications. Furthermore, with the explosion of Big Data, there is a requirement for innovative methods and infrastructures to collect, analyze, and derive meaningful insights from the vast amount of data generated. This necessitates the integration of computational and storage capabilities, databases, sensors, and human collaboration. Future Generation Computer Systems aims to pioneer advancements in distributed systems, collaborative environments, high-performance computing, and Big Data analytics. It strives to stay at the forefront of developments in grids, clouds, and the Internet of Things (IoT) to effectively address the challenges posed by these wide-area, fully distributed sensing and computing systems.
期刊最新文献
SWIM: Sliding-Window Model contrast for federated learning Heterogeneous system list scheduling algorithm based on improved optimistic cost matrix The Fast Inertial ADMM optimization framework for distributed machine learning Review of deep learning-based pathological image classification: From task-specific models to foundation models Learning protein language contrastive models with multi-knowledge representation
×
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