摘要
高效利用短时交通流数据进行预测,建立合理的预测模型对于有效缓解交通拥挤问题十分必要.首先获取时间序列数据,判断序列的平稳性,然后用Eviews软件对时间序列数据构建ARIMA!6,1,6"模型,通过最小二乘估计法进行参数估计,并对残差检验是否为白噪声数据,对该ARIMA模型进行交通量的静态预测,最后对预测结果做出评价,结果显示拟合效果较好,表明ARIMA模型在短时交易量预测时有很大的应用价值.
It is necessary to effectively use short-term traffic flow data for forecasting and establish a reasonable forecasting model to effectively alleviate traffic congestion. Firstly, time series data are obtained to judge the stability of the sequence.Then, Eviews software is used to build ARIMA (6,1, 6)model for the time series data. The least squares estimation method is used to estimate the parameters. The residual error is checked to see if it is white noise data. The ARIMA model is used for static traffic volume prediction. Finally, the prediction results are evaluated. The results show that the fitting effect is good, indicating that ARIMA model has great application value in short-term transaction volume prediction.
作者
刘学刚
张腾飞
韩印
LIU Xuegang;ZHANG Tengfei;HAN Yin(Management School,University of Shanghai for Science and Technology,Shanghai 200093,China)
出处
《物流科技》
2019年第12期91-94,102,共5页
Logistics Sci-Tech
