A simple and effective method for predicting travel times on freeways

We present a method to predict the time that will be needed to traverse a given section of a freeway when the departure is at a given time in the future. The prediction is done on the basis of the current traffic situation in combination with historical data. We argue that, for our purposes, the current traffic situation of a section of a freeway is well summarized by the current status travel time. This is the travel time that would result if one were to depart immediately and no significant changes in traffic would occur. This current status travel time can be estimated from single- or double-loop detectors, video data, probe vehicles, or any other means. Our prediction method arises from the empirical observation that there exists a linear relationship between any future travel time and the current status travel time. The slope and intercept of this relationship may change subject to the time of day and the time until departure, but linearity persists. This observation leads to a prediction scheme by means of linear regression with time-varying coefficients.

[1]  Hani S. Mahmassani,et al.  System Optimal Dynamic Assignment for Electronic Route Guidance in a Congested Traffic Network: Dynamic Flow Modelling and Control , 1995 .

[2]  N. L. Johnson,et al.  Multivariate Analysis , 1958, Nature.

[3]  P C Vythoulkas,et al.  ALTERNATIVE APPROACHES TO SHORT TERM TRAFFIC FORECASTING FOR USE IN DRIVER INFORMATION SYSTEMS , 1993 .

[4]  Xiaoyan Zhang,et al.  Short-term travel time prediction , 2003 .

[5]  Maurice Aron,et al.  ATHENA, PREVISION A COURT TERME DU TRAFIC SUR UNE SECTION DE ROUTE [ ATHENA, A METHOD FOR SHORT TERM INTER-URBAN TRAFFIC FORECASTING] , 1994 .

[6]  R. Tibshirani,et al.  Varying‐Coefficient Models , 1993 .

[7]  Dongjoo Park,et al.  Forecasting Multiple-Period Freeway Link Travel Times Using Modular Neural Networks , 1998 .

[8]  H. Nicholson,et al.  The prediction of traffic flow volumes based on spectral analysis , 1974 .

[9]  I Okutani,et al.  Dynamic prediction of traffic volume through Kalman Filtering , 1984 .

[10]  Mascha C. van der Voort,et al.  The KARIMA method - Combining Kohonen maps with arima time series model to forecast traffic flow , 1996 .

[11]  Petros A. Ioannou,et al.  Traffic flow modeling and control using artificial neural networks , 1996 .

[12]  T. Oda.  An algorithm for prediction of travel time using vehicle sensor data , 1990 .

[13]  Ismail Chabini,et al.  Discrete Dynamic Shortest Path Problems in Transportation Applications: Complexity and Algorithms with Optimal Run Time , 1998 .

[14]  Peter J. Bickel,et al.  Day-to-Day Travel-Time Trends and Travel-Time Prediction from Loop-Detector Data , 2000 .

[15]  Yorgos J. Stephanedes,et al.  FREEWAY INCIDENT DETECTION THROUGH FILTERING , 1993 .

[16]  Chao Chen,et al.  The PeMS algorithms for accurate, real-time estimates of g-factors and speeds from single-loop detectors , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[17]  Ariel Orda,et al.  Minimum weight paths in time-dependent networks , 1991, Networks.

[18]  Mark Dougherty,et al.  SHOULD WE USE NEURAL NETWORKS OR STATISTICAL MODELS FOR SHORT TERM MOTORWAY TRAFFIC FORECASTING , 1997 .