基于时间序列的机场短时段值机客流量预测

Short-Term Passenger Flow Forecasting for the Check-in Process in the Airport Based on Time Series

在机场向数字化运营的转型过程中,为了实现航站楼内高效的运作以及资源的合理分配,从而对短时段的值机客流量的预测提出了更高的要求。通过对机场历史数据的统计和分析,结合航班的DOW特性,分析值机客流量的相关影响因素,以每小时的值机客流量为研究对象,构建基于时间序列的动态回归ARIMAX模型。实验结果表明,上述模型相对于传统的预测模型,预测精度更高,拟合效果更精确,有效地预测了航站楼内短时段的值机旅客人数,为航站楼内资源的动态分配和优化提供了不可或缺的决策支持。

In the course of the transformation of airport operation toward the digital operation, in order to achieve the efficient operation and the rational distribution of resources in the terminal, a higher demand is put forward for the prediction of the passenger flow in the short period. Through statistics and analysis of airport historical data, the relevant influencing factors of passengers’ traffic in the check-in process were analyzed by combining with the DOW characteristics of flights. Using hourly check-in passenger flow as research object, this paper established a dynamic regression ARIMAX model based on time series. The experimental results show that the model is more accurate than the traditional prediction model, and its fitting effect is more accurate. It effectively predicts the number of passengers during the short-term check-in process in the terminal, thus providing an indispensable decision support for dynamic allocation and optimization of the resources within the terminal building.