Study on the Synthetic Link Travel Time Prediction Model of Key Theory of ITS
-
摘要: 行程时间预测是智能运输系统研究的一个重要问题。为此, 建立了许多算法, 有历史趋势方法、非参数回归模型、时间序列方法、神经网络、卡尔曼滤波、交通模拟和动态交通分配模型等。然而, 在变化的交通状况和任意时段的条件下, 这些方法和模型都不能取得令人满意的预测结果。在总结这些已有的预测方法和模型的基础上, 提出了一种综合模型Abstract: Travel time prediction is one of important problems of ITS research. Some predictive models including historic profile approaches, non parametric regression, time series, neural networks, Kalman filtering, traffic simulation and dynamic traffic assignment models, etc., have been established. None of them can obtain satisfactory predictive results at any time of day and/or under different traffic conditions. On the basis of overviewing the existing prediction models, a synthetic model is proposed.
-
Key words:
- ITS /
- dynamic route guidance /
- travel time prediction model
-
表 1 各种模型预测误差比较
模型种类 MSE RMSE MAE MAX-ARE MARE EC 历史趋势方法 375.3354 19.3736 11.9542 1.0793 0.1553 0.8839 多元回归模型 128.7141 11.3452 8.8714 0.3864 0.1181 0.9284 ARIMA (2, 1, 0) 230.8334 15.1932 11.2364 0.5620 0.1418 0.9028 神经网络 115.2169 10.7339 8.4671 0.4419 0.1118 0.9322 综合模型 99.6280 9.9814 8.2812 0.1141 0.1082 0.9333 
下载: 导出CSV
-
[1] NOBUO NISHI, ETSUJI KURODA, etc. Evaluation for effectiveness of CDRGS[R]. Proceeding of 4th ITS World Congress, Berlin, 1997. [2] SHBAKLO S, BHAT C, KOPPELMAN F, LI J, TH- AKURIAH P, SEN A, ROUPHAIL N. Short-term travel time prediction[R]. ADVANCE Project Report, TRF-TT-01, 1992, Illinois University Transportation Research Consortium. [3] JEFFREY D J, RUSSAM K, ROBERTSON D I. Electronic route guidance by AUTOGUIDE: the research background[J]. Traffic Engineering and Control, 1987, 28(3): 525-529. [4] SMITHB L, DEMETSKY M J. Traffic flow forecasting: comparison of modeling approaches[J]. Journal of Transportation Engineering, 1997, 123 (4): 262-266. [5] YOUNG-IHN LEE, CHAN YOUNG CHOI. Development of link travel time prediction algorithm for urban expressway[R]. Proceedings of 5th World Congress on ITS, Korea, 1998. [6] JINSOO YOU, TSCHANGHO. Toward developing an expert GIS-based travel time forecasting model with congression pattern analysis[R]. Proceeding of 5th World Congress on ITS, Korea, 1998. [7] GAULT HE. An on-line measure of delay in road traffic computer controlled systems[J]. Traffic Engineering and Control, 1981, 22(7): 602-605. -
点击查看大图
图(2) / 表(1)
计量
- 文章访问数: 277
- HTML全文浏览量: 98
- PDF下载量: 350
- 被引次数: 0
