基于小波神经网络的短时交通流量预测算法的研究

Study on Short-term Traffic Flow Prediction Algorithm Based on Wavelet Neural Network

随着城市的快速发展,汽车保有量急剧增加,交通日益拥堵,传统的固定时长红绿灯系统不合理配时是造成这种情况的主要原因。运用小波神经网络算法进行未来交通流预测研究,同时通过MATLAB软件平台结合微观仿真软件VISSIM4.30进行虚拟仿真。实验结果表明:基于小波神经网络可用于预测短期交通流量,整体精度可达到90%或更高,本算法与固定时长和BP神经网络算法对比,能大幅度提高车辆通行量。

With the rapid development of the city, the number of cars has increased dramatically, and the traffic has become increasingly congested. The unreasonable timing of the traditional fixed-time traffic light system is the main cause of this situation. The wavelet neural network algorithm is used to predict the traffic flow in the future. At the same time, the MATLAB software platform combined with the micro-simulation software VISSIM4.30 is used to simulate the traffic flow in the future. The experimental results show that the wavelet neural network can be used to predict the short-term traffic flow, and the overall accuracy can reach 90% or higher. Compared with the fixed time length and BP neural network algorithm, the proposed algorithm can greatly improve the vehicle traffic volume.