Queuing length prediction method in multi-source traffic information environment

Abstract

The invention belongs to the field of traffic control, specifically a queuing length prediction method in a multi-source traffic information environment. The method comprises the steps: enabling parking point data of a floating vehicle to be matched with an extracted normal queuing parking point on an intersection segment at first, and judging a lane group where the parking point belongs through a driving path of the floating vehicle; calculating the maximum distance between the queuing parking point of the floating vehicle and an intersection, calculating a moment when the floating vehicle passes by an exit detector at an upstream intersection, determining a parking wave velocity again, calculating a queuing state evolution point, calculating the position of a start wave and finally judging the maximum queuing length. The method provided by the invention achieves the accurate prediction of the queuing length at the intersection, provides strong support for the reasonable setting of signal control parameters, and is of great significance to the traffic congestion in an active mode of taking preventive measures.

Description

technical field [0001] The invention belongs to the field of traffic control, in particular to a queue length prediction method in a multi-source traffic information environment. Background technique [0002] The queuing length is an important decision variable for traffic signal control. Accurately calculating the queuing length of vehicles under different load conditions at an intersection is an important prerequisite for rationally formulating signal control parameters. Especially at adjacent critical intersections, the queue length of vehicles at oversaturated intersections will be periodically accumulated due to the constraints of traffic capacity, and even the queues will go back to the previous intersection, resulting in deadlock of traffic flow. Therefore, accurate calculation of vehicle queuing length is of great significance for proactive traffic congestion control. The classic methods and technical difficulties in the study of queuing length at intersections can ...

AI Technical Summary

Problems solved by technology

However, the difficulty of these models is that it is difficult to estimate the existing parking quantity, that is, the initial queuing length, especially in the case of multiple queuing parking situations, the prediction error may continue to accumulate, reducing the calculation accuracy of queuing length

[0006] Fourth, traffic flow feature extraction for congestion control must consider the physical association and traffic flow coupling of associated intersections (upstream and downstream intersections), and cannot be performed only for a single intersection

Especially in the state of critical saturation or local oversaturation of traffic flow, the mutual influence between adjacent intersections in the road network is becoming more and more prominent, and even the queuing length of downstream intersections extends to upstream intersections, resulting in local congestion. Even worsened into a large area of ​​congestion

Images