Project · University of Amsterdam1 min read

Centralized Vehicle Control for Traffic Congestion in Smart City using Agent-based Model

An agent-based highway model in which a central controller takes over vehicles. In simulation, flow rose from about 1,500 to about 2,500 vehicles an hour, a gain of 67%.

GitHub repositoryarkdong/traffic-agent-model

This project tried to investigate how effectively a centralised takeover strategy can mitigate traffic congestion in simulated highway based on agent-based model. This was done through the reproduction of an already existent agent-based model based on a paper by 1. The model was expanded upon by adding agent behaviour for multiple lanes and logic that simulates a central controller. It was hypothesized that centralized vehicle takeover will be significantly more effective than human-based models in mitigating congestion. This was confirmed as the central vehicle takeover managed to increase the average speed of the vehicles and maintain a higher flow under congested conditions.

Enhanced highway traffic throughput by 67% in simulation by implementing and evaluating centralized vehicle-takeover strategies. Flow improvement from ~1500 veh/h to ~2500 veh/h

My Role

  • Developed dynamic data visualization and delivered a research poster and elevator pitch with excellent structure and quality, resulting a grade of 9/10.

Visualization

Two ring-road plots of simulated vehicles, each dot coloured by its speed in metres per second

Poster

The research poster: traffic congestion control by centralized vehicle takeover in a smart city with an agent-based model

Footnotes

  1. Zhang, Fa, Jinling Li, and Qiaoxia Zhao (2005). “Single-lane traffic simulation with multi-agent system”. In: Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005. IEEE, pp. 56–60. ↩

Published
30 Jan 2025
Topics
UvA, Model