Predicting and Optimizing Traffic Flow at Toll Plazas

Robert Neuhold, Filippo Garolla, Oliver Sidla, Martin Fellendorf

Research output: Contribution to journalConference articleResearchpeer-review

Abstract

This study proposes a model for predicting traffic flow and an algorithm to optimize lane allocation in front of an Austrian toll plaza. The traffic prediction model uses local traffic data from the motorway and is based on time series analysis. The prediction is structured into three levels: trend prediction for all calendar days in the year, long-term prediction for the current day and short-term prediction for the next hour. The error of long-term prediction was less than 15% per hour over the whole day. An optimization algorithm for better lane allocation was developed by using a camera based traffic state detection system at the toll plaza. Based on the measured queue lengths per toll gate lane, the algorithm shifts vehicles to lower queued areas in front of the toll plaza. Therefore, the algorithm was able to reduce travel times up to 6% in daily average and queue lengths with more than 100m up to 30% per lane. The prediction model and optimization algorithm are not site-specific and can also be applied on different toll plazas or bottlenecks on motorways (e.g. road works, border crossing, motorway junction etc.).

Original languageEnglish
Pages (from-to)330-337
Number of pages8
JournalTransportation Research Procedia
Volume37
DOIs
Publication statusPublished - 2019

Fingerprint

traffic
local traffic
Time series analysis
time series analysis
Travel time
Cameras
travel
road
trend

Keywords

  • Cluster
  • Optimization algorithm
  • time series analysis
  • Traffic flow modeling
  • Traffic prediction
  • Traffic state detection

ASJC Scopus subject areas

  • Transportation

Fields of Expertise

  • Sustainable Systems

Cite this

Predicting and Optimizing Traffic Flow at Toll Plazas. / Neuhold, Robert; Garolla, Filippo; Sidla, Oliver; Fellendorf, Martin.

In: Transportation Research Procedia, Vol. 37, 2019, p. 330-337.

Research output: Contribution to journalConference articleResearchpeer-review

Neuhold, Robert ; Garolla, Filippo ; Sidla, Oliver ; Fellendorf, Martin. / Predicting and Optimizing Traffic Flow at Toll Plazas. In: Transportation Research Procedia. 2019 ; Vol. 37. pp. 330-337.
@article{fb1943800917410ea6e5f7d287568963,
title = "Predicting and Optimizing Traffic Flow at Toll Plazas",
abstract = "This study proposes a model for predicting traffic flow and an algorithm to optimize lane allocation in front of an Austrian toll plaza. The traffic prediction model uses local traffic data from the motorway and is based on time series analysis. The prediction is structured into three levels: trend prediction for all calendar days in the year, long-term prediction for the current day and short-term prediction for the next hour. The error of long-term prediction was less than 15{\%} per hour over the whole day. An optimization algorithm for better lane allocation was developed by using a camera based traffic state detection system at the toll plaza. Based on the measured queue lengths per toll gate lane, the algorithm shifts vehicles to lower queued areas in front of the toll plaza. Therefore, the algorithm was able to reduce travel times up to 6{\%} in daily average and queue lengths with more than 100m up to 30{\%} per lane. The prediction model and optimization algorithm are not site-specific and can also be applied on different toll plazas or bottlenecks on motorways (e.g. road works, border crossing, motorway junction etc.).",
keywords = "Cluster, Optimization algorithm, time series analysis, Traffic flow modeling, Traffic prediction, Traffic state detection",
author = "Robert Neuhold and Filippo Garolla and Oliver Sidla and Martin Fellendorf",
year = "2019",
doi = "10.1016/j.trpro.2018.12.200",
language = "English",
volume = "37",
pages = "330--337",
journal = "Transportation Research Procedia",
issn = "2352-1465",
publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Predicting and Optimizing Traffic Flow at Toll Plazas

AU - Neuhold, Robert

AU - Garolla, Filippo

AU - Sidla, Oliver

AU - Fellendorf, Martin

PY - 2019

Y1 - 2019

N2 - This study proposes a model for predicting traffic flow and an algorithm to optimize lane allocation in front of an Austrian toll plaza. The traffic prediction model uses local traffic data from the motorway and is based on time series analysis. The prediction is structured into three levels: trend prediction for all calendar days in the year, long-term prediction for the current day and short-term prediction for the next hour. The error of long-term prediction was less than 15% per hour over the whole day. An optimization algorithm for better lane allocation was developed by using a camera based traffic state detection system at the toll plaza. Based on the measured queue lengths per toll gate lane, the algorithm shifts vehicles to lower queued areas in front of the toll plaza. Therefore, the algorithm was able to reduce travel times up to 6% in daily average and queue lengths with more than 100m up to 30% per lane. The prediction model and optimization algorithm are not site-specific and can also be applied on different toll plazas or bottlenecks on motorways (e.g. road works, border crossing, motorway junction etc.).

AB - This study proposes a model for predicting traffic flow and an algorithm to optimize lane allocation in front of an Austrian toll plaza. The traffic prediction model uses local traffic data from the motorway and is based on time series analysis. The prediction is structured into three levels: trend prediction for all calendar days in the year, long-term prediction for the current day and short-term prediction for the next hour. The error of long-term prediction was less than 15% per hour over the whole day. An optimization algorithm for better lane allocation was developed by using a camera based traffic state detection system at the toll plaza. Based on the measured queue lengths per toll gate lane, the algorithm shifts vehicles to lower queued areas in front of the toll plaza. Therefore, the algorithm was able to reduce travel times up to 6% in daily average and queue lengths with more than 100m up to 30% per lane. The prediction model and optimization algorithm are not site-specific and can also be applied on different toll plazas or bottlenecks on motorways (e.g. road works, border crossing, motorway junction etc.).

KW - Cluster

KW - Optimization algorithm

KW - time series analysis

KW - Traffic flow modeling

KW - Traffic prediction

KW - Traffic state detection

UR - http://www.scopus.com/inward/record.url?scp=85062242633&partnerID=8YFLogxK

U2 - 10.1016/j.trpro.2018.12.200

DO - 10.1016/j.trpro.2018.12.200

M3 - Conference article

VL - 37

SP - 330

EP - 337

JO - Transportation Research Procedia

JF - Transportation Research Procedia

SN - 2352-1465

ER -