Optimal decentralized signal control for platooning in connected vehicle networks

Hoang, The Anh; Walton, Neil; Vu, Hai L.

Abstract

In the last decade, pressure-based schemes such as Back Pressure and Max Weight algorithms have been widely researched and applied for traffic signal control due to their simplicity and proven throughput maximization. In such algorithms, the next chosen signal phase at an intersection in a road network is the one with the highest measured weight, representing the pressure of traffic movements at the intersection, determined based on a single characteristic of the traffic flow or vehicles’ state at that intersection. This paper develops a new optimal Max Weight control mechanism to enhance the network throughput and reduce vehicle delays in a network using a concept of platooning enabled by Connected Vehicles (CVs). To this end, we propose a new proven optimal Max Weight control scheme where the weight consists of several features including the platoon delay, as well as the speed and position of vehicles within the platoon. To the best of our knowledge, this work is the first to propose a platoon pressure-based concept considering multiple configurable attributes in formulating the pressure. Furthermore, we provide a rigorous stability proof that ensures the throughput optimality of the proposed control scheme. In addition, we also develop a machine learning procedure in this paper to optimize the weighting parameter of each attribute contributing to the total pressure enabling its seamless deployment in practice. A number of simulation results demonstrate the feasibility of the learning procedure and show that our Max Weight platoon pressure-based scheme outperforms the state-of-the-art and well-known existing pressure-based algorithms.

Citation

Hoang, T. A., Walton, N., & Vu, H. L. (2024). Optimal decentralized signal control for platooning in connected vehicle networks. Transportation Research Part C: Emerging Technologies, 167, Article 104832. https://doi.org/10.1016/j.trc.2024.104832

• Journal Article Type: Article
• Acceptance Date: Aug 19, 2024
• Online Publication Date: Sep 2, 2024
• Publication Date: 2024-10
• Deposit Date: Oct 24, 2024
• Publicly Available Date: Oct 24, 2024
• Journal: Transportation Research Part C: Emerging Technologies
• Print ISSN: 0968-090X
• Electronic ISSN: 1879-2359
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 167
• Article Number: 104832
• DOI: https://doi.org/10.1016/j.trc.2024.104832
• Public URL: https://durham-repository.worktribe.com/output/2983057