Control Strategy for Ramp Traffic Based on Improved ALINEA Algorithm

This study presents a ramp control strategy that builds upon the ALINEA framework to enhance the throughput of expressways equipped with vehicles-to-everything capabilities. The conventional ALINEA control strategy relies on input flow data from the previous cycle, which may not accurately reflect the current traffic conditions. To overcome this limitation, the gate recurrent unit is employed to predict the current traffic volume, serving as an improved input flow. Furthermore, a novel combined ramp control strategy is proposed in consideration of the driver's tolerance level under the constraints of ramp queuing. This combined strategy selectively employs different ramp control methods based on the varying queuing conditions of vehicles on the ramp. A comparative analysis with the conventional ALINEA control strategy reveals that the improved ALINEA approach can reduce total travel times by up to 9.84% in merging area, concurrently reducing ramp queues length by 23.30%. The research used predicted traffic parameters for ramp control, which is a new framework for achieving active traffic control on ramp. In addition, the ramp control strategy takes into account the balance between the ramp and the main line, which is very helpful for avoiding the influence of ramp vehicles on adjacent urban streets.