A Dynamic and Deadline-Oriented Road Pricing Mechanism for Urban Traffic Management

作     者：Jiahui Jin Xiaoxuan Zhu Biwei Wu Jinghui Zhang Yuxiang Wang Jiahui Jin;Xiaoxuan Zhu;Biwei Wu;Jinghui Zhang;Yuxiang Wang

作者机构：the School of Computer Science and EngineeringSoutheast UniversityNanjing 211189China the Department of Computer Science and EngineeringHangzhou Dianzi UniversityHangzhou 310018China 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2022年第27卷第1期

页      面：91-102页

核心收录：

学科分类：12[管理学] 0202[经济学-应用经济学] 02[经济学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 020205[经济学-产业经济学] 08[工学] 082303[工学-交通运输规划与管理] 0823[工学-交通运输工程] 

基　　金：supported by the National Key R&D Program of China(No.2018AAA0101200) National Natural Science Foundation of China(Nos.62072099,61972085,62072149,and 61872079) Public Welfare Research Program of Zhejiang(No.LGG19F020017) Jiangsu Provincial Key Laboratory of Network and Information Security(No.BM2003201) Key Laboratory of Computer Network and Information Integration of Ministry of Education of China(No.93K-9) “Zhishan”Scholars Programs of Southeast University partially supported by Collaborative Innovation Center of Novel Software Technology and Industrialization the Fundamental Research Funds for the Central Universities 

主　　题：road pricing traffic congestion al eviation deep reinforcement learning 

摘      要：Road pricing is an urban traffic management mechanism to reduce traffic ***,most of the road pricing systems based on predefined charging tolls fail to consider the dynamics of urban traffic flows and travelers’demands on the arrival *** this paper,we propose a method to dynamically adjust online road toll based on traffic conditions and travelers’demands to resolve the above-mentioned *** method,based on deep reinforcement learning,automatically allocates the optimal toll for each road during peak hours and guides vehicles to roads with lower toll ***,it further considers travelers’demands to ensure that more vehicles arrive at their destinations before their estimated arrival *** method can increase the traffic volume effectively,as compared to the existing static mechanisms.