Minghui Ma , Xu Han , Shidong Liang , Yansong Wang , Lan Jiang
{"title":"Connected vehicles ecological driving based on deep reinforce learning: Application of Web 3.0 technologies in traffic optimization","authors":"Minghui Ma , Xu Han , Shidong Liang , Yansong Wang , 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":"163 ","pages":"Article 107544"},"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}
引用次数: 0
Abstract
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.
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.