基于状态空间模型的动态交通出行量预测研究

Research on Dynamic Traffic Volume Prediction Based on State Space Model

在现代交通管理中,短时交通信息预测有着非常重要的地位。动态交通出行量作为重要的交通信息之一,对其进行预测研究可以丰富短时交通信息预测的理论研究,为提前实施相应的交通管理策略,引导交通需求,提高路网利用效率提供数据支撑。本文在总结动态交通出行量反推理论的基础上,构建了用于动态交通出行量预测的状态空间模型,描述了卡尔曼滤波算法。最后将模型和算法应用到南京某路网进行预测计算,结果表明所构建的模型具有较高的预测准确性。

In modern traffic management,short-term traffic information prediction plays a very important role.Dynamic traffic volume,as one of the important traffic information,can enrich the theoretical research of short-term traffic information prediction by conducting prediction research on dynamic traffic volume.It provides data support for implementing corresponding traffic management strategies in advance,guiding traffic demand,improving road network utilization efficiency,and providing data support.On the basis of summarizing the theory of dynamic traffic volume inversion,this article constructs a state space model for dynamic traffic volume prediction and describes the Kalman filtering algorithm.Finally,the model and algorithm were applied to a certain road network in Nanjing for prediction calculation,and the results showed that the constructed model had high prediction accuracy.