Intersection signal timing control optimization method and device

Abstract

The invention discloses an intersection signal timing control optimization method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of acquiring a state-action-reward sample set, wherein the state-action-reward sample set comprises state-action-reward sub-sample sets of at least one intersection; based on a neural network and the state-action-reward sample set, performing training to obtain a traffic state simulator; and on the basis of enhanced learning, the state-action-reward sample set and the traffic state simulator, performing training to obtain a signal timing control model. According to the method and the device, the traffic state simulator can be obtained by training based on a neural network model and the state-action-reward sample set, and the signal timing control model is obtained by training based on the traffic simulator and the enhanced learning. The problem that simulated data does not conform to actualtraffic conditions and is inaccurate due to collection or assumption of multiple traffic parameters in the prior art is solved, and the universality and flexibility are improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for optimizing timing control of intersection signals. Background technique [0002] With the continuous advancement of the urbanization process and the continuous increase of car ownership, traffic congestion has become a common problem plaguing major cities. In addition to the congestion caused by the excessive traffic flow in the road network, the unreasonable timing of intersection signal lights will also cause additional intersection time delays, resulting in unnecessary congestion. [0003] In the prior art, the signal timing of some intersections adopts a timing control mechanism, that is, the traffic signal controller at the intersection operates according to several preset timing schemes, and a certain fixed timing scheme is adopted within a certain period of time , where the signal timing is the ratio of red, yellow, and green lights in each direc...

AI Technical Summary

Problems solved by technology

It solves the problem that the simulated data is out of touch with the actual traffic conditions due to the collection or assumption of multiple traffic parameters in the prior art, and improves the universality and flexibility

Images