Published on July 22, 2024
Antonio Pellicer
Scientific Researcher
Advanced traffic management solutions play a crucial role in enhancing mobility, reducing congestion and ensuring resilient multimodal services. By leveraging cutting-edge technologies such as AI-driven algorithms, real-data analytics and simulation, these solutions empower cities to respond effectively to traffic incidents, foster multimodal connectivity and optimize transport network performance.
But how can cities and authorities effectively utilize and implement these integrated multimodal solutions to master network and traffic management? One answer night be a toolbox such as the one developed by the EU-funded SYNCHROMODE research project.
The SYNCHROMODE team aim to develop a toolbox, where a suite of services and modules will be combined to improve overall transport network management, helping to coordinate different agents involved in the provision and control of the transport services. In this sense, SYNCHROMODE will provide to transport managers and authorities with new predictive and network optimization capabilities for balancing transport supply and demand and reacting to different network disturbances.
The services integrated within the SYNCHROMODE toolbox are:
Or maybe network disturbances to make it clearer?
In SYNCHROMODE, Aimsun is primarily leading the simulation-based demand-supply interaction modelling task and plays a major role estimating and predicting traffic demand using data-driven approaches.
The team is working on improving the efficiency and accuracy of methods for offline estimation of the traffic demand. The process of estimating Origin-Destination (OD) traffic demand using simulation-based optimization is complex and can be computationally intensive for large-scale models. In SYNCHROMODE we propose novel methods for demand estimation, that combine Machine-Learning techniques and optimization approaches and do not rely on traffic simulations. Aimsun’s research uses neural networks to emulate traffic simulation, enabling analytical gradient calculations and backpropagation to improve the efficiency and accuracy of the estimated demand.
Additionally, the team is also developing a deep learning (DL) model to predict traffic demand from traffic observations (e.g. flow measurements from loop detectors) and offline estimated demand matrices for the network of interest.
Aimsun is also supporting the SYNCHROMODE partners by developing transport simulation models to virtually assess traffic management strategies and by integrating optimisation-based modules into simulation tools.
The proposed approaches will be demonstrated and validated through three Case Studies (CS) in Madrid (Spain), South Holland region (The Netherlands) and Thessaloniki (Greece).
Leveraging the excess capacity of Public Transport (PT) during off-peak hours for last-mile delivery, this CS aims to integrate urban last-mile delivery using Demand-Responsive Transport (DRT) with PT services. The SYNCHROMODE toolbox will assist users in predicting and estimating PT and parcel delivery demand, optimizing parcel placement within buses, enhancing bus and DRT services for both passengers and parcels.
Aimsun will contribute to this CS by simulating the optimised and combined DRT-Bus routes in the Aimsun Ride simulation platform for on-demand services. The team has also been working on improving the multimodal PT trip routing and simulation in Aimsun Ride, which involves the computation of an optimal sequence of mode-specific trips with alternative transport modes (e.g., walk, car, bike, scooter, etc.) to access and egrees PT (bus, rail, metro, tram, etc.).
The Province of South Holland is facing major mobility challenges due to the increasing number of visitors during warm and sunny days. Roads accessing the Keukenhof flower park and the coastline of the province are experiencing congestion and delays. Additionally, major large-scale infrastructure roadworks are planned for the upcoming years, which might exacerbate the impacts on the road network.
Aimsun, in collaboration with the University of Deusto, University College London UCL and BeMobile, are developing a methodology to optimise (and prioritise) the sequence of multi-day roadworks considering simulation-based traffic-related indicators.
In addition, Aimsun is applying the demand estimation module in the Beach and Keukenhof Use Cases. A preliminary exercise was carried out using traffic data from 2023 of the entire region of The Netherlands. After formatting and cleaning the data, traffic patterns were extracted from the historical data, using clustering algorihtms. Results from this analysis showed 4 main patterns representing how traffic moves in the Netherlands (see Figure 3). The identified patterns were used to adjust the historical demand (OD) matrices. Upcoming work will further delimitate the study area to the beach and Keukenhof sites to focus on identifying patterns for beach/Keukenhof days and estimate the demand for these specific days to be included into the transport model.
Thessaloniki’s western entrance faces significant congestion, with most travellers using low-occupancy private vehicles. There’s a need to promote PT, shared vehicles and available parking areas to alleviate this issue. Aimsun is contributing to this Use Case by developing a microscopic model of a signalized arterial (Leoforos Nikis) and testing C-ITS apps at signalized intersections for pedestrians and eBikes. ‘Illegal’ behaviours such as ‘red-light violation’ or ‘jaywalking’ will also be considered in the simulation to complement the analysis.
In just 15 months, SYNCHROMODE has already made a significant impact by developing innovative methodologies that will pave the way for more efficient and integrated tools to enhance traffic management. Exciting months lie ahead as we intensify our efforts to finalise the development of methodologies and apply them to the case studies by the end of the year.
For further information and regular content updates, visit the SYNCHROMODE homepage or follow SYNCHROMODE project on LinkedIn for regular updates!
SHARE
Aimsun Next 24
Aimsun (2024). Aimsun Next 24 User’s Manual, Aimsun Next Version 24.0.0, Barcelona, Spain. Accessed on: April. 16, 2024. [Online].
Available: https://docs.aimsun.com/next/24.0.0/
Aimsun Next 24
@manual {AimsunManual,
title = {Aimsun Next 24 User’s Manual},
author = {Aimsun},
edition = {Aimsun Next 24.0.0},
address = {Barcelona, Spain},
year = {2024. [Online]},
month = {Accessed on: Month, Day, Year},
url = {https://docs.aimsun.com/next/24.0.0},
}
Aimsun Next 24
TY – COMP
T1 – Aimsun Next 24 User’s Manual
A1 – Aimsun
ET – Aimsun Next Version 24.0.0
Y1 – 2024
Y2 – Accessed on: Month, Day, Year
CY – Barcelona, Spain
PB – Aimsun
UR – [In software]. Available:
https://docs.aimsun.com/next/24.0.0/
