摘要
实时、准确的短时交通流量预测是智能交通系统(ITS)中的一个关键问题。本文先介绍一种基于AR(p)模型的线性最小方差自适应预测算法。它采用带遗忘因子的递推最小二乘方法进行参数估计,采用基于线性最小方差预报原理的Astrom预报算法进行预报。在该算法的基础上提出了一种改进的多步自适应预测方法。新算法增加了误差补偿项,能较好地满足时变模型的预测要求。针对大量实测数据进行仿真实验,结果表明:改进算法在应用于时变性强的短时交通流量多步预测时具有较好的预测性能,而且其预测性能优于线性最小方差预报算法。
Real-time and accurate short-term traffic flow forecasting has become critical in intelligent transportation systems (ITS).A kind of adaptive linear minimum square error forecasting method adopting AR(p) model was introduced.In this method the recursive forgetting factor least square method (RFFLS) was adopted for parameter estimation.The Astrom forecasting algorithm was used for forecasting,which is based on linear minimum square error of forecasting.Then based on this method an improved multi-step adaptive forecasting method was presented.The error compensation item was added to this new method which could well meet the needs of forecasting for time-variant models.A lot of real observation data are used for simulation tests and the results show that when the improved method is applied to the strong time-variant multi-step short-term traffic flow forecasting,it has good forecasting performance which is superior to the linear minimum square error forecasting methods.
出处
《公路交通科技》
CAS
CSCD
北大核心
2005年第1期115-118,共4页
Journal of Highway and Transportation Research and Development
关键词
短时交通流预测
自适应预测
多步预测
线性最小方差预测
Short-term traffic flow forecasting
Adaptive forecasting
Multi-step forecasting
Linear minimum square error forecasting