Single-intersection signal timing optimization method based on trajectory data

Abstract

The invention discloses a single-intersection signal timing optimization method based on trajectory data. The method comprises the following steps of: acquiring original signal timing information of an intersection; acquiring historical trajectory data of floating vehicles in the same time period on a road section associated with the intersection, and solving queuing positions of the floating vehicles in each period; predicting the queuing length in each phase of the period of the intersection according to a Bayesian model and a probability distribution theory; and calculating the optimal timing duration of each phase on the basis of a starting wave theory. According to the method, the actual situation that the permeability of current road network floating vehicles is low is comprehensively considered, and different methods are adopted to calculate traffic scenes with different permeability. According to the method of the invention, the intersection queuing length estimation method iscombined with the traffic wave theory to carry out timing on the intersection; the massive trajectory data are fully utilized; the advantages of statistics and traffic wave theory are fully combined;the intersection signal timing method based on the trajectory data is established; the utilization rate of green light duration of each phase is improved; and the delay of the intersection is effectively reduced.

Description

technical field [0001] The invention relates to the technical field of traffic control, in particular to a single intersection signal timing optimization method based on track data. Background technique [0002] The rapid development of traffic theory and Internet technology provides diverse and large-scale traffic data resources for traffic research and urban traffic management. Electronic police data, bayonet data, and coil data have disadvantages such as difficulty in laying, high maintenance costs, and missing data. With the rise of online taxis, massive trajectory data has been collected. Trajectory data is also highly respected in the research field due to its high precision and large sample size. [0003] In the current existing research, trajectory data are mostly used to estimate traffic parameters, such as traffic flow, queue length, intersection delay and travel time, etc. In the paper "Queue length estimation from probe vehicle location and the impacts of sampl...

AI Technical Summary

Problems solved by technology

However, the direct application of trajectory data to single-intersection timing has not yet been studied.

Images