A method and device for dividing traffic control multi-level sub-areas

Abstract

The present application relates to the technical field of intelligent traffic control, in particular, to a method and device for dividing traffic control into multi-level sub-areas. In order to solve the problems of unreasonable division of single-level sub-area, low similarity of sub-area traffic, and redundant nodes in sub-area. The method includes: when the number of nodes in the K-level sub-area is greater than a preset threshold, dividing the K-level sub-area by a self-defined spectral clustering function to obtain the K+1-level sub-area; removing the K+1-level sub-area Obtain the final K+1-level sub-area relative to the redundant nodes in the K-level sub-area in the area; based on the final K+1-level sub-area, it is determined that there are undivided sub-areas in the K-level sub-area, then repeat The above steps are performed until all K-level sub-regions are divided; otherwise, the final K+1-level sub-region division results are output.

Description

technical field [0001] The present application relates to the technical field of intelligent traffic control, in particular, to a method and device for dividing traffic control into multi-level sub-areas. Background technique [0002] The urban road network is composed of hundreds of different types of signal intersections. In order to improve its stability and control efficiency, the traffic signal control system needs to divide the road network into multiple areas of different shapes. Each area is a traffic control system. Sub-area, which consists of multiple closely connected adjacent signalized intersections. [0003] In the implementation of some traffic control sub-areas, the road network topology is usually divided into static sub-areas based on historical traffic data and regional terrain characteristics; in other traffic control sub-area divisions, clustering algorithms are used to achieve The dynamic first-level sub-area division of the traffic road network to ada...

AI Technical Summary

Problems solved by technology

[0005] This application provides a method and device for dividing multi-level sub-areas of traffic control. By determining the relationship between the number of sub-area nodes and the threshold, constructing a custom spectral clustering function, constructing an average silhouette coefficient, and removing redundant nodes in the sub-area, certain To a certain extent, it can solve the problems of unreasonable division of single-level sub-areas, low similarity of sub-area traffic, and redundant nodes in sub-areas

Images