基于ARIMA与人工神经网络组合模型的交通流预测

将自回归求和滑动平均(ARIMA)与人工神经网络组合模型用于短时交通流预测。利用ARIMA模型良好的线性拟合能力和人工神经网络强大的非线性关系映射能力,把交通流时间序列看成由线性自相关结构和非线性结构两部分组成,采用ARIMA模型对交通流序列的线性部分进行预测,用人工神经网络模型对其非线性残差部分进行预测。结果表明:组合模型的预测准确性高于各自单独使用时的准确性;组合方法发挥了2种模型各自的优势,是短期交通流预测的有效方法。

Traffic Flow Prediction Based on Hybrid ARIMA and ANN Model

Hybrid autoregressive integrated moving average(ARIMA) and artificial neural network models were employed in the short-term traffic flow prediction.Using the good linear fitting ability of ARIMA and the strong nonlinear mapping ability of artificial neural network,the traffic flow time series was considered to be composed of a linear autocorrelation structure and a nonlinear structure.ARIMA model was used to predict the linear component of traffic flow time series and the artificial neural network model was applied to the nonlinear residual component prediction.Results show that the hybrid model,which takes advantage of the unique strength of the two models in linear and nonlinear modeling,can produce more accurate predictions than that of single model.The hybrid model can be an efficient method to the short-term traffic flow prediction.