Single-point signalized intersection optimization timing method based on Fisher ordered clustering

Abstract

The invention discloses a single-point signalized intersection optimization timing method based on Fisher ordered clustering. The method comprises the steps of: extracting historical traffic flow data, and carrying out dimension reduction processing, and obtaining a dimension-reduced historical traffic flow matrix; taking a row vector of the dimension-reduced historical traffic flow matrix as a sample, and segmenting the sample by adopting the Fisher ordered clustering to obtain an optimal segmentation number and a segmentation mode corresponding to the optimal segmentation number, and taking the optimal segmentation number and the segmentation mode as an optimal control time period; and carrying out an optimal timing simulation experiment on the optimal control time period to obtain an optimal timing scheme. According to the method, the traffic efficiency of an intersection can be improved under the condition of high saturation of the intersection; The method overcomes the high requirements of an existing adaptive control method for infrastructures such as hardware and algorithms, and has the advantages of low cost and high reliability.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, and relates to a method for optimizing the timing of single-point signalized intersections based on Fisher ordered clustering. Background technique [0002] With the rapid development of the economy and the rapid development of science and technology, the innovation of automobiles is also undergoing important changes, and the way people travel has undergone tremendous changes. Followed by many traffic problems, such as traffic jams, traffic accidents, etc., these problems have affected the normal flow of traffic, solving these traffic problems plays a decisive role in the normal operation of the road traffic network. The single-point intersection is the most basic unit of the urban road traffic network in our country, and it has obvious effects to solve traffic problems from the point of view of the single-point intersection. [0003] The signal control schemes of single-point...

AI Technical Summary

Problems solved by technology

Timing control can quickly respond to the traffic demand in the case of low saturation, but it cannot effectively improve the traffic efficiency of the intersection in the case of high saturation and oversaturation

The working principle of induction control is to lay sensors on the entrance lane of the intersection to detect the traffic flow of the intersection entrance lane in real time, thereby changing the signal light timing scheme and responding to the traffic demand of the intersection in real time, but the actual application cost of induction control is too high

Adaptive control also detects the traffic flow at the intersection through sensors, and then uploads the real-time traffic flow to the host computer. The host computer generates the optimal timing scheme based on the real-time traffic flow data. This timing method can maximize the efficiency of intersection traffic , but the cost is relatively higher, which requires the cooperation of sensors, host computer hardware, algorithms and other infrastructure

Images