基于计算实验的城市道路行程时间预测与建模

城市道路行程时间预测对于提高交通管控效果具有重要意义. 本文综合应用平行系统、集散波、误差反馈修正、多模型自适应控制及模型库动态优 化策略等方法与技术对间断流行程时间预测问题进行了研究. 首先,介绍了平行系统理论的基本原理及计算实验的基本方法; 然后,给出了基于平行系统理论的路段行程时间的预测模型, 设计了基于集散波的行程时间计算实验方法, 提出了多模型自适应行程时间预测并给出了模型动态优化策略. 最后,通过实验证明了本方法的有效性. 结果表明, 本文方法预测精度较高, 且能够对行程时间预测值进行持续优化, 可为后续的间断流行程时间预测研究提供借鉴.

Urban Road Travel Time Prediction and Modeling via Computational Experiments

Urban road travel time prediction is of great significance to improve the effect of traffic management and control. In this paper, integrated applications of methods and technologies are studied such as parallel systems, traffic waves, error feedback amendment, multi-models adaptive control, and the dynamic optimization strategies for multi-models to the prediction problems of disconnect traffic flow. Firstly, the basic principles of parallel systems theory and the methods of computational experiments are introduced. Then, the prediction model of link travel time based on the theory of parallel systems is given, and the methods of computational experiments of travel time based on the traffic waves are designed. More over, multi-models adaptive travel time prediction models as well as dynamic optimization strategies are put forward. Finally, the effectiveness of the proposed method is shown through the analysis of experimental results. The proposed method provides a higher precision and continuous optimization of travel time prediction, it also provides a reference for the following travel time prediction of disconnect traffic flow.