Journal
INTELLIGENT DISTRIBUTED COMPUTING XIV
Volume 1026, Issue -, Pages 125-134Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-96627-0_12
Keywords
-
Categories
Funding
- MSIT (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW [20170001000051001]
- National Research Foundation of Korea (NRF) - Korea government (MSIP) [NRF-2019K1A3A1A80113259]
Ask authors/readers for more resources
This paper proposes a distributed cooperative negotiation method for optimizing traffic flow by utilizing collective learning algorithm and exchanging routing information among connected vehicles. Simulation results show that the proposed method performs better in high traffic demand scenarios.
Traffic congestion has an impact on traffic efficiency and the quality of life. To address this issue, this paper proposes a distributed, cooperative negotiation method for connected vehicles in traffic flow optimization. In particular, when the connected vehicles obtain the traffic congestion alerts from the roadside units, they exchange their routing information and distribute the traffic flows across the roads by using a collective learning algorithm that does not rely on a centralized controller. Results exported from Simulation of Urban Mobility show that the proposed method outperforms traditional routing methods. In a high traffic demand scenario, the average travel time of the proposed method decreases by 35% and 12% compared with the shortest path routing and the dynamic traffic routing methods, respectively.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available