Link and Route Travel Time Prediction Including the Corresponding Reliability in an Urban Network Based on Taxi Floating Car Data

Abstract

This study addressed the modeling of route travel times (including their associated uncertainty) in urban networks based on taxi floating car data. The model decomposes observed link travel speeds into the expected speed (modeled with daily and seasonal profiles) and deviations thereof. The latter were shown to be strongly heteroscedastic by providing an explicit model for the time variance. Temporal and spatial correlations were considered with a vector autoregression framework. Modeling was supported by automatic model selection methods for identifying the relevant effects and providing one-step-ahead predictions. The potential of the proposed model was investigated with taxi floating car data from a real-world test site near the city core of Vienna, Austria. Various specifications of the vector autoregression model were tested and compared. Taxi floating car measurements of local speeds were found to be strongly heteroscedastic, a factor that must be considered in estimation of models for expected travel speeds. The modeling of the mean suggested no remaining daily or weekly patterns, and it was superior to simple models explaining travel speeds as a linear function of the travel speeds in the last time period. The variance model successfully captured heteroscedasticity. More complex models for link travel speeds, including temporal and spatial correlation, do not increase prediction accuracy consistently; the lack indicates that a sampling frequency of 15 min for floating car data in urban settings is too low for use of temporal dependencies for prediction. An introduced method for computing route travel time uncertainty showed variability over the day for a highly frequented route.

Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data

“…Conventional studies based on GPS data regarding traffic state include congestion detection (Montero, Pacheco, Barcelo, Homoceanu, & Casanovas, 2016), link or route travel time, speed and distance measurements (Tulic, Bauer, & Scherrer, 2014;Jiménez-Meza, Arámburo-Lizárraga, & Fuente 2013); detecting urban road network accessibility (Cui et al, 2016). Most of these studies only focus on peak hours and only use descriptive statistics without deep analysis about influencing factors for time, speed, distance, etc.…”

Transferring urban traveling speed model fits across cities

“…Stathopoulos and Karlaftis [19] develop multivariate ARIMA and state space models in a setting similar to ours and obtain MAPEs between 12-20 %. Tulic et al [22] investigate the Vienna taxi FCD in detail. They also build multivariate autoregressive models for a smaller number of links.…”

Travel time predictions: should one model speeds or travel times?

“…The raw measurements of link travel times are aggregated in 15-min time intervals providing for each link and each 15-min interval an average link travel time as well as a count of taxis contributing to the travel time measurement. More details on the data collection process can be found in [12].…”

“…Based on the location information over time, algorithms for inferring link travel times have been discussed in the literature (see for instance [12] for a discussion using the same data base as in this paper). Typically link travel time estimates are temporally aggregated into time-ofday-intervals for every given link.…”

“…In this paper the issue is investigated empirically for a large floating taxi dataset in Vienna. We apply the modelling methodology of [12] to local speeds and link travel times. We demonstrate that it depends on the measure of accuracy whether modelling speeds or travel times directly leads to better performance.…”