Traffic signal light control model based on evolutionary programming algorithm optimization BP neural network

In this paper, evolutionary programming algorithm through the mutation operator and the selection strategy to find the optimal individual, used to initialize the BP neural network's weights and threshold value. Through this way, we can improve the training efficiency, speed up the convergence rate, increase the irregularity of the weights and threshold value, avoid BP neural network training into locally optimal solution. In this paper, the evolutionary programming algorithm optimization BP neural network is applied to the traffic signal light control, according to the historical traffic flow data of a crossroad to predict the next node's traffic flow data, and then through the predicted traffic flow data to re-adjust the traffic signal light frequency, to improve traffic congestion and other traffic problems. The experimental results show that evolutionary programming algorithm optimization BP neural network has a good effect on traffic signal light optimization.