Saved in:
Bibliographic Details
Main Author: Georgios Kyriakopoulos
Format: Recurso digital
Language:
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.16950674
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902189941719040
author Georgios Kyriakopoulos
author_facet Georgios Kyriakopoulos
contents <p>This release provides <strong>3 trace files</strong> containing <strong>Floating Car Data (FCD)</strong> from <strong>10-hour microscopic traffic simulations of central Athens</strong>, generated with the <strong>SUMO (Simulation of Urban MObility)</strong> toolkit.</p> <p>Each simulation reflects distinct conditions and configurations.</p> <ol> <li><strong>train-fcd</strong> - Training simulation on the base network</li> <li><strong>test-fcd</strong> - Test simulation on the base network</li> <li><strong>rain-fcd</strong> - Simulation on the rain-modified network (with reduced friction on all lanes)</li> </ol> <p>These files are now available in both <strong>CSV</strong> and <strong>Parquet</strong> format. The output is organized by <strong>timestep </strong>and for each <strong>vehicle</strong> that is in the simulation at that timestep a row of its <strong>id, x, y, speed, lane, odometer, fuel,</strong> and <strong>waiting </strong>is logged.</p> <p>Each simulation has a duration of 10 hours, spanning from morning to afternoon. There is a traffic pattern applied, with morning and afternoon peaks and lower mid-day activity. This traffic pattern is described by a list of per-hour traffic generation periods. On that list, some noise is added for each simulation, using a different random seed for each one. The same random seed is also used together with the traffic generation periods to generate the random trips used for each simulation. The goal was to introduce realistic variability, without going completely off a common traffic pattern.</p> <p>For the generation of this synthetic dataset, the following tools were used.</p> <ul> <li><strong>osmGet </strong>– Extract OpenStreetMap data from a bounding box over central Athens</li> <li><strong>osmBuild </strong>– Convert OSM data into a SUMO-compatible network</li> <li><strong>randomTrips </strong>– Generate random trips based on per-hour traffic generation periods</li> <li><strong>sumo </strong>– Run the microscopic simulation and export FCD data</li> </ul>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_16950674
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Synthetic 10-Hour Traffic Simulations for Central Athens (Train/Test/Rain)
Georgios Kyriakopoulos
<p>This release provides <strong>3 trace files</strong> containing <strong>Floating Car Data (FCD)</strong> from <strong>10-hour microscopic traffic simulations of central Athens</strong>, generated with the <strong>SUMO (Simulation of Urban MObility)</strong> toolkit.</p> <p>Each simulation reflects distinct conditions and configurations.</p> <ol> <li><strong>train-fcd</strong> - Training simulation on the base network</li> <li><strong>test-fcd</strong> - Test simulation on the base network</li> <li><strong>rain-fcd</strong> - Simulation on the rain-modified network (with reduced friction on all lanes)</li> </ol> <p>These files are now available in both <strong>CSV</strong> and <strong>Parquet</strong> format. The output is organized by <strong>timestep </strong>and for each <strong>vehicle</strong> that is in the simulation at that timestep a row of its <strong>id, x, y, speed, lane, odometer, fuel,</strong> and <strong>waiting </strong>is logged.</p> <p>Each simulation has a duration of 10 hours, spanning from morning to afternoon. There is a traffic pattern applied, with morning and afternoon peaks and lower mid-day activity. This traffic pattern is described by a list of per-hour traffic generation periods. On that list, some noise is added for each simulation, using a different random seed for each one. The same random seed is also used together with the traffic generation periods to generate the random trips used for each simulation. The goal was to introduce realistic variability, without going completely off a common traffic pattern.</p> <p>For the generation of this synthetic dataset, the following tools were used.</p> <ul> <li><strong>osmGet </strong>– Extract OpenStreetMap data from a bounding box over central Athens</li> <li><strong>osmBuild </strong>– Convert OSM data into a SUMO-compatible network</li> <li><strong>randomTrips </strong>– Generate random trips based on per-hour traffic generation periods</li> <li><strong>sumo </strong>– Run the microscopic simulation and export FCD data</li> </ul>
title Synthetic 10-Hour Traffic Simulations for Central Athens (Train/Test/Rain)
url https://doi.org/10.5281/zenodo.16950674