Travel time prediction for congested freeways with a dynamic linear model

TL;DR

This paper introduces a dynamic linear model approach for predicting travel times on congested freeways, demonstrating significant accuracy improvements over existing methods, especially for short-term forecasts.

Contribution

The paper presents a novel application of dynamic linear models to traffic prediction, capturing non-linear traffic states through time-varying parameters, and compares its performance with other models.

Findings

DLM-based predictions outperform traditional methods in accuracy.

Significant improvements in short-term travel time forecasting.

Effective modeling of non-linear traffic dynamics.

Abstract

Accurate prediction of travel time is an essential feature to support Intelligent Transportation Systems (ITS). The non-linearity of traffic states, however, makes this prediction a challenging task. Here we propose to use dynamic linear models (DLMs) to approximate the non-linear traffic states. Unlike a static linear regression model, the DLMs assume that their parameters are changing across time. We design a DLM with model parameters defined at each time unit to describe the spatio-temporal characteristics of time-series traffic data. Based on our DLM and its model parameters analytically trained using historical data, we suggest an optimal linear predictor in the minimum mean square error (MMSE) sense. We compare our prediction accuracy of travel time for freeways in California (I210-E and I5-S) under highly congested traffic conditions with those of other methods: the instantaneous travel time, k-nearest neighbor, support vector regression, and artificial neural network. We show significant improvements in the accuracy, especially for short-term prediction.