|Title:||V2X-assisted integrated lane-changing and variable speed limit control for weaving segments|
|Advisors:||Ho, Ivan (EIE)|
Hong Kong Polytechnic University -- Dissertations
|Department:||Department of Electronic and Information Engineering|
|Pages:||87 pages : color illustrations|
|Abstract:||With the rapid growth of traffic demand, the weaving concentration problem is significant on the highway, resulting in decreased operation efficiency and road safety. The cooperative intelligence transportation system (C-ITS) with vehicle-to-everything (V2X) technology provided the possibility for emerging new cooperative strategies to alleviate that problem. In this research, two traffic control strategies are proposed and investigated along with the integrated strategy of the two control methods. One is the longitude lane-changing (LC) distribution strategy, which is verified in a real V2X simulation environment by sending LC advisory messages to connected vehicles (CV) via a roadside unit (RSU) and tested under different packet loss rate scenarios. The other one is the variable speed limit (VSL) control strategy based on the deep deterministic policy gradient (DDPG) algorithm of reinforcement learning (RL).|
In terms of simulation platform, a joint-simulator-based digital twin platform is applied for verification of the proposed algorithm, in which traffic simulator SUMO models traffic network and vehicular mobility, and network simulator OMNeT++ establishes a V2X communication environment.
The results indicate that LC control alleviates the concentration area at around 50 m to 150 m by distributing LC behaviors more evenly. When the packet loss rate is lower than 0.2, LC advisory control brings a positive effect on the traffic performance, but it reduces the road efficiency when the packet loss is higher than 0.4. On the other hand, the RL-based VSL control algorithm has limited effect on mitigating the concentrated LC behaviors, but it can improve the overall traffic efficiency in terms of average speed and travel time. In comparison, the integrated strategy has the most effective impact on alleviating LC concentration as well as improving vehicle mobility performance. In addition, the RL-based VSL control can compensate for the impact of serious packet loss on LC control to a certain extent, which can effectively improve the traffic efficiency especially under poor communication situations.
|Rights:||All rights reserved|
Files in This Item:
|6520.pdf||For All Users (off-campus access for PolyU Staff & Students only)||7.25 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: