Traffic light scheduling method and system based on iterative learning model predictive control

Abstract

The invention discloses a traffic signal light dispatching method and system based on iterative learning model predictive control, and relates to the field of intelligent traffic. The method includes the following steps: step 1, establishing a traffic flow simulation model in a target area; step 2, according to the control strategy Obtain closed-loop data of a fixed time interval; step 3, perform predictive control using the closed-loop data as the terminal condition of the subsequent open-loop predictive optimization problem. The present invention firstly starts from the traditional fixed-time traffic signal scheduling strategy, generates data by iteration and then iterates, and uses the previous closed-loop data to obtain the optimal traffic flow pattern, and further based on some simulations, it proves that the method proposed by the present invention using historical iteration The iterative learning model predictive control strategy of the closed-loop data set as the terminal constraint of the day's predictive control optimization problem can reduce the queuing time of vehicles on the road and make the vehicles pass faster and more smoothly in the traffic network.

Description

technical field [0001] The invention relates to the field of intelligent traffic, in particular to a traffic signal light scheduling method and system based on iterative learning model predictive control. Background technique [0002] The congestion of urban traffic network will bring serious pollution and economic cost, and traffic light control is one of the effective ways to alleviate traffic congestion. Traffic light scheduling is an important topic in traffic engineering. For the urban traffic network, road sections and intersections always encounter the problem of heavy traffic flow, which brings troubles to the current traffic control strategy. [0003] At present, most of the signalized intersections adopt the method of controlling the signal lights in a predetermined cycle or a fixed time interval. This method is based on the traffic demand observed in the past, and pre-sets the timing scheme for control. This scheme cannot respond in time to the random changes in...

AI Technical Summary

Problems solved by technology

This method is based on the traffic demand observed in the past, and pre-sets the timing scheme for control. This scheme cannot respond to random changes in traffic demand in a timely manner.

However, the existing learning model predictive control scheme in this field is to establish a "safety assessment data set" by collecting all previous iteration trajectories. Since this set is composed of points, the convexity of the terminal set cannot be guaranteed. However, the establishment of terminal cost and terminal constraint set often leads to mixed integer quadratic programming (MIQP) problem

Images