一种基于ARIMA 模型的短时交通流量改进预测算法.pdf

一种基于 ARIMA 模型的短时交通流量改进预测算法* 1 1，2 1 张利 ，李星毅 ，施化吉 （1.江苏大学 计算机科学与通信工程学院，江苏镇江 212013; 2.北京交通大学 电子信息工程学院，北京 100044） 摘 要： 实时准确的短时交通流量预测是城市交通控制与诱导的基础，也是智能交通系统的重要功能之一。 本文分析了造成基于线性最小方差预报原理的Astrom算法在多步预测过程中误差逐步增大的原因，并在该 算法基础上增加误差动态修正因子，提出一种改进的短时交通流量预测算法。针对大量实测数据进行仿真 实验，并引入多个统计量进行误差分析。 结果表明: 改进算法在应用于时变性强的短时交通流量预测时相 对于Astrom算法具有更好的预测性能。 关键词：时间序列预测;短时交通流预测;ARIMA模型;改进预测算法;动态修正因子 An Improved Short--term traffic flow forecast algorithms based on ARIMA model 1,2 1 1 LI Xing-yi ，Zhang Li ，Shi Hua-ji (1.School of Computer Science and Telecommunications Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China; 2.Advanced Control Systems Lab School of Electronics and Information Engineering, Beijing Jiao Tong University, Beijing 100044,China) Abstract: The real time forecast for short-time traffic flow is the foundation of urban traffic control and guidance, which is also one of main functions of intelligent transportation system. This paper first analyzed which had made Astrom algorithm based on the linear smallest variance forecast principle that the probable error increased gradually in many step forecast process, and increased the error dynamic modification factor in this algorithm foundation, then proposed one kind of improvement short-time traffic flow forecast algorithm. A lot of real observation data were used for simulation tests and a number of statistics were introduced to analyze the errors. The results show that the improved algorithm has better forecast performance than Astrom algorithm when applied to