基于小波和Kalman滤波的交叉口流量组合预测

Combination Prediction of Traffic-Volume in Intersections Based on Wavelet Analysis and Kalman Filter

为更准确地预测动态变化的道路交叉口流量,根据城市道路流量分布的特点,提出了在小波分析和离散Kalman滤波的基础上进行组合预测的方法.这种方法将路口的流量数据构造成几个相关序列,对每个序列分别进行小波变换和Kalman预测,然后将各序列的预测值组合成最终结果.这种预测方法可用于其他动态流量预测,如路段流量预测、路口流量分配预测等.实验表明,该方法可以有效地减少预测误差,并具有较好的鲁棒性.

Based on the analysis of the distribution characteristics of urban traffic-volume, a combination prediction method based on wavelet analysis and Kalman filter was proposed to obtain more precise information on traffic-volume in intersections. With this method, some correlative data serials from an intersection are constructed, each data serial is treated respectively with Kalman filter and wavelet transfer, and the final result is formed from the predicted results of these serials. This method may be widely applied in the fields of dynamic traffic prediction, such as the predictions of road-sect traffic-volume and traffic-volume distribution of intersections. Experimental results show that the method can evidently decrease errors in the prediction and shows preferable robustness.