Heuristic random searching traffic signal timing optimization method and system

Abstract

The invention belongs to the field of intelligent traffic systems, and particularly relates to a heuristic random searching traffic signal timing optimization method, aiming at solving the problems ofhigh complexity and long optimization time of the conventional traffic signal timing optimization method. The method comprises the steps of respectively superposing 2N exploration noises on the basis of a phase duration vector formed by a timing scheme of a road section to be optimized to obtain 2N performance indexes; obtaining N performance indexes through the selection of the optimal performance indexes and the negation operation of the corresponding exploration noise, and adjusting the phase duration vectorby using a preset adjustment algorithm based on the N performance indexes; repeatedly executing the above steps based on the adjusted phase time length vector until a preset iteration termination condition is reached, and outputting the phase duration vector obtained by the last iteration as optimization. According to the invention, the traffic intersection signal timing scheme can be optimized within an acceptable time range under the condition of limited computing resources,the robustness is good, and the implementation is strong.

Description

technical field [0001] The invention belongs to the field of intelligent traffic systems, in particular to a heuristic random search traffic signal light timing optimization method and system. Background technique [0002] In Intelligent Transportation Systems (ITS) systems, the timing scheme of signal lights at traffic intersections has a significant impact on traffic efficiency. Many researchers and engineers have realized that a good timing scheme is the most important factor in the current intelligent transportation system, which can effectively alleviate traffic congestion and improve travel efficiency. [0003] In the traffic scene, there is no clear mapping relationship between the signal control scheme d and the congestion situation w that can calculate the gradient Therefore, how to alleviate traffic congestion by optimizing the control scheme has not been a good way. The existing signal light timing schemes are mainly divided into the following three categories,...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problems of high complexity and long optimization time in the existing traffic signal light timing optimization method, the first aspect of the present invention proposes a heuristic random search traffic signal light When optimizing method, this method comprises the following steps:

Images