基于交通流参数相关的阻塞流短时预测卡尔曼滤波算法  

Kalman filter algorithm for short-term jam traffic prediction based on traffic parameter correlation

作　　者：董春娇[1] 邵春福[2] 周雪梅[3] 孟梦[2] 诸葛承祥[2] 

机构地区：[1]田纳西大学交通研究中心 [2]北京交通大学城市交通复杂系统理论与技术教育部重点实验室,北京100044 [3]同济大学教育部道路与交通工程重点实验室,上海210804

出　　处：《东南大学学报（自然科学版）》2014年第2期413-419,共7页Journal of Southeast University：Natural Science Edition

基　　金：国家自然科学基金资助项目(51178032)

摘　　要：提出一种考虑交通流参数相关关系的卡尔曼滤波算法,实现阻塞流状态下道路网交通流短时预测.在交通流守恒方程的基础上,借鉴偏微分方程求解Lax-Wendroff格式离散的思想,结合阻塞流状态下交通流时间和空间特性及进出口匝道等因素的影响,建立阻塞流状态下交通流短时预测状态空间模型,并设计基于卡尔曼滤波方法的模型求解算法.最后以北京市某一区域路网为例,进行了实证性研究.研究结果表明:所建立的阻塞流状态下交通流短时预测卡尔曼滤波算法由于同时考虑了时间和空间因素,能够使预测平均绝对百分比误差(MAPE)控制在10%以内;平均MAPE仅为7.96%.相同条件下,ARIMA模型和Elman模型预测MAPE分别为19.88%和10.51%.A Kalman filter model considering the correlation property of traffic flow parameters is proposed to realize network short-term traffic flow prediction under jam traffic.The proposed state-space model of short-term traffic flow prediction is presented by solving the conservation equation u-sing Lax-Wendroff scheme.In addition,the spatial-temporal characteristics of the traffic flow on ur-ban expressway networks and the influence factors of on and off ramp are taken into account for flow rate prediction.The estimation algorithm of the proposed state-space model is designed based on the Kalman filter method.A region expressway network in Beijing is taken as an example to evaluate the performance of the proposed method.The results show that the maximum prediction mean absolute percentage error（MAPE）of the proposed Kalman filter model is less than 10%since the input of the Kalman filter model considers the impacts of spatial-temporal characteristics,and the mean of predic-tion MAPE is 7.96%.For the same predicted conditions,the mean prediction MAPEs of ARIMA and Elman model are 19.88% and 10.5 1%,respectively.

关 键 词：交通流短时预测 阻塞流状态 状态空间模型 卡尔曼滤波 

分 类 号：U491.1[交通运输工程—交通运输规划与管理]