基于Box-Cox指数变换改进的ARIMA模型交通流预测方法  

Improved ARIMA Model Traffic Flow Prediction Method Based on Box-Cox Exponential Transformation

作　　者：李文勇 李俊卓 王涛 LI Wenyong;LI Junzhuo;WANG Tao(School of Architecture and Transportation Engineering,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学建筑与交通工程学院,桂林541004

出　　处：《武汉理工大学学报（交通科学与工程版）》2020年第6期974-977,共4页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家自然科学基金项目资助(61963011)。

摘　　要：由于交通流量的日变化趋势带来的长期自相关性引起了交通流量时间序列的异方差性,使差分自回归移动平均模型在交通流量预测中预测精度降低.针对此问题,提出一种改进的方法应用于交通流量预测.该改进方法通过Box-Cox指数变换建立了观测交通流量数据均值和方差之间的函数关系,并由此推导了交通流量时间序列的方差齐次转换函数,有效消除了非平稳的交通流量时间序列的长期自相关引起的异方差性.结果表明:改进后的ARIMA模型由于考虑了长期自相关引起的异方差性这一非线性特性,相比非平稳的HoltWinter模型,具有更小的平均绝对百分误差和均方根误差,在低流量时刻能提供更为精确的置信区间.Due to the long-term autocorrelation caused by the daily trend of traffic flow leads to the heteroscedasticity of traffic flow time series,auto—Regression Intergrated Moving is reduced in the prediction accuracy of traffic flow forecast.In response to this problem,an improved method is proposed for traffic flow prediction,which establishes the functional relationship between the mean and variance of the observation traffic flow data through Box-Cox transformation,and thus deduces the variance conversion function of the traffic flow time series.Due to the heteroscedasticity caused by long-term autocorrelation of non-stationary traffic flow time series is eliminated,the results show that the improved ARIMA model has a smaller mean absolute percentage error and root mean square error than the non-steady HoltWinter model,and can provide a more accurate confidence interval at low flow times.

关 键 词：交通工程 交通流时间序列 长期自相关性 异方差性 ARIMA模型 

分 类 号：U491.1[交通运输工程—交通运输规划与管理]