Airport aprons are complex, multi-node operational hubs frequently affected by queue congestion resulting from control handovers, taxi conflicts, and external factors. To enable proactive congestion management, we propose a new and accurate method for apron queue length prediction. The core of our approach is a multi-queue network model in which queues are systematically divided by control position and taxi direction. This framework, which applies the Fluid Flow Approximation and is calibrated with historical data, effectively captures the dynamics of multi-node traffic flow. In a validation case study at Beijing Daxing International Airport (ZBAD), the model achieved high accuracy, with the mean absolute error of queue length prediction averaging 0.5 aircraft. The results demonstrate the model’s ability to characterize queue dynamics on a minute-level scale across a full day.
Li et al. (Fri,) studied this question.