摘要
针对区间道路短时车流量数据规律性较弱、随机误差干扰较强,且具有高度不确定性、难以准确预测的问题,基于ARIMA算法提出了一种改进型的短时车流量预测模型。该模型的建立无需借助任何外生变量,根据需要预测的时间周期个数可将短时车流量数据划分为对应的数据集组,再由每个数据集组预测下一个时间周期的车流量。该模型使得数据更加平滑,有效解决了多因素对短时车流量的影响。对区间道路采集到的车流量数据进行建模仿真,仿真结果验证了所提模型的普适性及准确性。
Aiming at the problems of weak regularity,strong random error interference and high uncertainty of short-term traffic flow data,it is difficult to predict accurately.Based on ARIMA algorithm,an improved short-term traffic flow prediction model is proposed.The establishment of the model does not need any exogenous variables,and according to the number of time periods that need to be predicted,the short-term traffic flow data is divided into corresponding data set groups,and the traffic flow of the next time period is predicted by each data set group.The model makes the data smoother and effectively solves the influence of multi factors on short-term traffic flow.The traffic flow data collected from the section road is modeled and simulated,and the simulation results verify the universality and accuracy of the proposed model.
作者
杨东龙
YANG Donglong(Tianjin University,Tianjin 300072,China)
出处
《电子设计工程》
2021年第13期38-42,共5页
Electronic Design Engineering
