A Freeway Exit Volume Prediction Method Based on Traffic Origin-Destination Stability Pattern

The traffic origin-destination (OD) data can be directly obtained from the freeway toll data. This information always reflects the vehicle status in temporal and spatial. And the OD information can also be used for making reasonable and effective predictions on the future trends of the freeway entrance volume. In this paper, an algorithm is proposed for predicting the freeway entrance volume based on the analysis of stability pattern of freeway traffic OD data. The contributions mainly include: (1) An information entropy-based method is presented for analyzing stability pattern of freeway traffic OD data; (2) Based on the stability pattern, a new prediction algorithm is applied on massive freeway entrance data. (3) The experimental results show that the proposed algorithm is reasonable and feasible, the accuracy is improved as well.

摘要从高速公路车辆出入口数据中可以直接提取路网中车辆的OD信息，这些信息可以从一定程度上反映出车辆在时空上的运行状态，更可以通过这类数据对高速公路出口流量的未来趋势做出合理有效地预测。本研究从真实数据出发，对交通路网中车辆OD的稳定性进行了分析，并以此为指导，将所得到的领域知识加入到常规的预测方法中，提出了一套基于OD稳定模式的高速公路出口流量预测方法。主要贡献包括：（1）提出了信息熵的概念,以刻画高速公路车辆OD的规律性；（2）提出了基于OD的稳定模式的出口流量预测方法；（3）在大量真实的数据上进行了实验分析。