Urban traffic jam identification method based on virus propagation theory

Abstract

The invention discloses an urban traffic jam identification method based on a virus propagation theory. The method comprises the following steps: 1, establishing an urban traffic jam propagation model based on the SIS virus propagation theory; 2, calculating the congestion proportion of the road section; and 3, recognizing the state of the road section based on the HHT model. Compared with the prior art, the method has the following positive effects: 1) simplicity: a simple virus propagation process is used to describe space-time characteristics of congestion in an urban road network during propagation, and the defect that a microscopic traffic flow model needs great data and calculation capability can be overcome, and the defect that a macroscopic traffic flow model cannot describe the propagation process can be overcome; and 2) accuracy: the HHT model is used for recognizing the traffic state of a road section and judging whether congestion happens or not, the algorithm can capture the change rule of traffic data in time, all internal information of original data is basically reserved, and balance between the data size and the information amount is achieved to a certain degree.

Description

technical field [0001] The invention relates to a method for identifying urban traffic jams based on virus transmission theory. Background technique [0002] The complex network characteristics of the urban road network make it difficult to identify urban traffic congestion. In order to identify the congestion in the urban traffic network and explore the rules of congestion propagation, many scholars have established congestion propagation models based on micro-models and macro-models. In these models, microscopic models are used to represent the precise characteristics of vehicles or road segments, which are computationally demanding and difficult to implement in large-scale networks. [0003] Different from microscopic models, macroscopic models are often used to describe the changing characteristics of traffic parameters and their interrelationships, such as queuing theory, traffic wave model, and machine learning methods. Specifically, the traffic wave model and queuing...

AI Technical Summary

Problems solved by technology

Although the results show that the prediction accuracy of the overall road network is high, the calibration of the parameters in the model requires a large amount of real-time data as a training set, and the prediction accuracy of the edge road sections needs to be improved

Images