基于时间序列与BP-ANN的短时交通流速度预测模型研究

Short-term traffic flow velocity prediction model based on time series and BP-ANN

针对现有的交通流速度预测模型使用唯一数据集且模型单一的问题,提出一种时间序列与人工神经网络相结合的预测模型。该模型通过时间序列分别对实时数据和历史数据建模预测,并应用人工神经网络调整实时数据和历史数据的预测值。实验结果表明该预测模型能够将预测误差控制在7%以内,且能够对不同输入参数下的短时交通流速度进行有效预测。

Aiming at the problem that the existing traffic flow velocity prediction model used a unique data set and a single model,this paper proposed a prediction model combining time series and artificial neural network.The model predicted real-time data and historical data by time series,and used artificial neural network to adjust the predicted values of real-time data and historical data.The experimental results show that the prediction model can control the prediction error within 7%and can effectively predict the short-term traffic flow speed under different input parameters.