Edge-Aware Hybrid-Action Reinforcement Learning for Latency-Sensitive Cooperative Bus Signal Priority in Vehicular Edge Networks

Abstract

Dense short-block road networks require bus signal priority (BSP) decisions to be generated and delivered within short and reliable control windows. This paper presents Edge-HyAR-BSP, a deadline-aware cooperative BSP framework that supports edge-side execution in vehicular edge networks. Roadside edge nodes perform decentralized low-latency inference, while the cloud supports centralized training and model updates. The framework represents each priority decision as a coupled phase-duration action and checks its executability under bus ETA, signal-safety, compensation, and edge-side deadline constraints. Green extension, red truncation, and cross-cycle compensation are integrated to improve bus passage while limiting disturbance to general traffic. The project platform covers 102 signalized intersections in the Rongdong District of Xiong'an New Area. Detailed operational evaluation is conducted on a 15-intersection corridor served by Route 302, while robustness and ablation analyses are performed in simulation using a topology derived from the 102-intersection network. In the selected pre-/post-deployment periods, bus speed increased by 14.64%-30.09%, aggregate bus delay decreased by 38.28%-65.13%, and bus stops decreased by 42.01%-58.62%. Edge deployment reduced mean end-to-end decision latency from 89.7 ms to 24.6 ms. Simulation results show gradual degradation under increased delay, packet loss, and workload. The findings provide operational case-study evidence for the feasibility of edge-aware hybrid-action BSP, while broader multi-route and cross-city validation remains necessary.