The invention discloses a method for predicting urban short-term traffic flow by an ARIMA (Autoregressive Integrated Moving Average) model facing a time sequence. The method comprises the following steps: S1, data collection: collecting traffic flow data shot by an electronic police at an urban road intersection; s2, data preprocessing: setting a data statistics time interval as 5 minutes to obtain traffic volume passing through a road within 5 minutes; s3, time sequence analysis: carrying out time sequence analysis on the preprocessed data, checking the stationarity of the time sequence, and carrying out stationary processing on a non-stationary sequence; and S4, constructing an ARIMA (p, d, q) model, and carrying out prediction fitting on the short-time urban traffic volume. The invention provides a new thought and method for predicting the short-time traffic volume, and has constructive significance for the management of urban roads.
本发明公开了一种面向时间序列的ARIMA模型对城市短时交通流预测的方法,包括步骤S1:数据收集:收集城市道路交叉口电子警察拍摄到的交通流量数据;步骤S2:数据预处理:把数据统计时间间隔设为5分钟,得到五分钟内的通过道路的交通量;步骤S3:时间序列分析:对预处理后的数据进行时间序列分析,检验时间序列的平稳性,对非平稳序列进行平稳化处理;步骤S4:构建ARIMA(p,d,q)模型,对短时城市交通量进行预测拟合。本发明为短时交通量的预测提供了一种新的思路和方法,对城市道路的管理具有建设性意义。
Method for predicting urban short-term traffic flow by using time sequence-oriented ARIMA (autoregressive integrated moving average) model
一种面向时间序列的ARIMA模型对城市短时交通流预测的方法
17.11.2023
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Transportation Research Record | 1999
|British Library Online Contents | 2016
|British Library Conference Proceedings | 1999
|