Traffic Signal Light Timing Optimization Based On Differential Evolution Of State-space Model Algorithm

The urban transportation industry is not only an important carrier of social and economic development,but also has an inseparable connection with the national economy.In recent years,with the rapid economic development,the number of cars is increasing at an explosive rate.The traditional signal light timing method cannot adapt to the complex traffic environment and the real-time and changeable traffic flow requirements.The effect of the traffic signal light timing method is affected by the performance of the control algorithm.Differential evolution algorithm is a kind of heuristic search intelligent optimization algorithm based on population.Although the differential evolution algorithm has the advantages of simple working principle,easy implementation,and strong stability,it also has some shortcomings,such as premature convergence and poor ability to jump out of local optimal solutions.In order to alleviate the negative impact of these shortcomings,a two-stage hybrid algorithm based on state space model and differential evolution algorithm is proposed.In the first stage of the algorithm,the reverse learning strategy is introduced in the population initialization stage of the differential evolution algorithm,and adaptive operators are used in the mutation stage to help maintain the diversity of the group during the search;the second stage is to use the improved state.The genetic algorithm based on state-space model further iteratively optimizes.Then,the hybrid algorithm was used to optimize the classical test functions and compared with the test results of the basic differential evolution algorithm and genetic algorithm based on state-space model.The experimental results showed that the hybrid algorithm not only improved the convergence speed,but also improved the convergence speed.On the premise of ensuring the accuracy of the algorithm’s convergence,the number of iterations is shortened,and the effectiveness of the algorithm in dealing with the optimization of multivariate complex functions is verified.Finally,according to the change of traffic flow before and after setting the left-turn waiting area,the calculation formula for the capacity of the left-turn lane containing the waiting area is analyzed,and the left-turn lane delay objective function is proposed.Considering the area to be turned left,taking the effective green light time of each phase as a variable and the minimum average delay of the vehicle as the objective function,a mathematical model for the optimization of intersection traffic light signal timing is constructed.The mathematical model is solved by the proposed hybrid algorithm,and the optimization plan for traffic light signal timing at intersections is obtained.The experimental results show that the hybrid algorithm can appropriately adjust the signal cycle length,redistribute the green light time of each phase,and reduce the average vehicle The delay rate verifies the effectiveness and feasibility of the hybrid algorithm applied to the signal timing optimization problem at intersections.