The invention provides an urban road network traffic flow prediction method based on a linear gray convolution model. The urban road network traffic flow prediction method comprises the following steps of: S1, selecting a to-be-predicted road section and screening out a related road section with relatively high correlation with traffic flow data of the to-be-predicted road section; S2, based on atraditional gray multivariable prediction model, establishing a linear gray convolution multivariable prediction model; and S3, according to the traffic flow data of the related road section, predicting the traffic flow of the to-be-predicted road section by using the linear gray convolution multivariable prediction model. Directed at the space-time characteristics of the urban road network traffic flow, the invention firstly proposes to apply the linear optimal gray convolution multivariable prediction model to predict the traffic flow, the model is more reasonable and higher in prediction precision than a gray univariate model, and is an improvement and perfection of the traffic flow prediction model.
本发明提出了一种基于线性灰色卷积模型的城市路网交通流预测方法,包括以下步骤:S1、选定待测路段并筛选出与待测路段交通流数据关联性较大的相关路段;S2、基于传统灰色多变量预测模型,建立线性灰色卷积多变量预测模型;S3、根据相关路段的交通流数据,运用线性灰色卷积多变量预测模型对待测路段交通流进行预测。本发明针对城市路网交通流的时空特性,首次提出运用线性优灰色卷积多变量预测模型对交通流进行预测,比灰色单变量模型更合理,预测精度更高,是对交通流预测模型的改进和完善。
Urban road network traffic flow prediction method based on linear gray convolution model
一种基于线性灰色卷积模型的城市路网交通流预测方法
2021-04-02
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Road section traffic flow prediction method based on time convolution neural network
European Patent Office | 2020
|Road network traffic flow prediction method based on gated loop graph convolution attention network
European Patent Office | 2023
|Traffic flow prediction method and system for urban road network
European Patent Office | 2021
|Traffic flow prediction method based on adaptive lightweight time convolution network
European Patent Office | 2024
|