Leveraging Edge Computing for Real-Time Traffic Management and Simulation with SUMO in Smart Cities
(2025) EITM02 20241Department of Electrical and Information Technology
- Abstract
- Traffic congestion is a persistent problem in modern urban environments, causing
delays, increasing pollution, and negatively affecting the quality of life of millions
of city dwellers. As urban populations grow, the need for intelligent traffic man-
agement systems becomes more pressing. This thesis presents a novel approach
to real-time traffic management using edge computing in conjunction with the
Urban Mobility Simulation (SUMO) tool. The Differential Evolution (DE) algo-
rithm is applied to optimize traffic signal timings, with the goal of minimizing
vehicle delays at multiple intersections within a simulated smart city. Using edge
computing, traffic data is processed locally, enabling faster responses and dynamic
... (More) - Traffic congestion is a persistent problem in modern urban environments, causing
delays, increasing pollution, and negatively affecting the quality of life of millions
of city dwellers. As urban populations grow, the need for intelligent traffic man-
agement systems becomes more pressing. This thesis presents a novel approach
to real-time traffic management using edge computing in conjunction with the
Urban Mobility Simulation (SUMO) tool. The Differential Evolution (DE) algo-
rithm is applied to optimize traffic signal timings, with the goal of minimizing
vehicle delays at multiple intersections within a simulated smart city. Using edge
computing, traffic data is processed locally, enabling faster responses and dynamic
adjustments to signal timings. The results of this approach demonstrate a sig-
nificant improvement in traffic flow efficiency, with reductions in vehicle delays in
various traffic scenarios. This research highlights the potential for combining edge
computing with evolutionary algorithms to address traffic congestion challenges in
modern cities. (Less) - Popular Abstract
- Imagine a city where traffic flows seamlessly, without the frustration of long waiting
times at the red lights or endless congestion during rush hour. With the rapid
growth of urban areas and the increasing number of vehicles on the road, traffic
management has become one of the most pressing challenges for modern cities.
Traditional traffic light systems, which operate on fixed schedules, often fail to
adapt to real-time traffic conditions, leading to unnecessary delays and pollution.
This research aims to change that by using cutting-edge technologies to make
traffic systems smarter, more efficient, and adaptive.
The core of this solution involves three powerful technologies: Edge Comput-
ing, the Simulation of Urban... (More) - Imagine a city where traffic flows seamlessly, without the frustration of long waiting
times at the red lights or endless congestion during rush hour. With the rapid
growth of urban areas and the increasing number of vehicles on the road, traffic
management has become one of the most pressing challenges for modern cities.
Traditional traffic light systems, which operate on fixed schedules, often fail to
adapt to real-time traffic conditions, leading to unnecessary delays and pollution.
This research aims to change that by using cutting-edge technologies to make
traffic systems smarter, more efficient, and adaptive.
The core of this solution involves three powerful technologies: Edge Comput-
ing, the Simulation of Urban Mobility (SUMO) tool, and the Differential Evolution
(DE) algorithm. By combining these technologies, we developed a system that
optimizes traffic light timings in real-time, significantly improving traffic flow in
urban areas.
Edge computing plays a crucial role in this solution. Unlike traditional sys-
tems that rely on centralized servers to process data, edge computing processes
information locally, right where the data is generated. In our case, this means
that traffic data collected at intersections is processed directly on-site, allowing
for faster decision-making. This reduces the delay time between sensing traffic
conditions and adjusting the lights, which is critical in busy urban environments
where every second counts.
To test and improve our traffic management system, we used SUMO, an open-
source traffic simulation tool. SUMO allowed us to create a virtual model of a
city and simulate real-world traffic scenarios. This enabled us to evaluate different
strategies for controlling traffic lights without having to test them in the real world
first. The Differential Evolution algorithm was then used to find the best possible
traffic light settings, focusing on reducing the time that vehicles spend idling at
intersections.
The Differential Evolution algorithm works much like a trial-and-error pro-
cess, but in a highly structured and efficient way. It starts by randomly selecting
different traffic light timings and then uses feedback from the simulation to evolve
and improve these timings over time. The goal of the algorithm is to minimize the
average delay for vehicles in the network, ensuring that traffic moves as smoothly
as possible.
Our results were promising. By using this smart combination of edge computing,
SUMO simulations, and the DE algorithm, we managed to reduce average
vehicle delays at intersections by more than 70%. This means that cars spend far
less time waiting at red lights, reducing not only the frustration for drivers but
also the amount of fuel wasted and emissions produced while idling.
This research has significant implications for the future of urban mobility.
Imagine every traffic light in a city being able to "think" and adapt in real time
based on the number of cars approaching the intersection. This kind of adaptive
traffic management system would lead to less congestion, lower pollution levels,
and a better quality of life for city residents. Moreover, by leveraging edge com-
puting, the solution is scalable and can be implemented without relying on vast,
centralized data centers, making it cost-effective and energy-efficient.
In the future, we hope to expand this system to include more advanced predic-
tive capabilities, perhaps using artificial intelligence to predict traffic jams before
they happen and adjust lights accordingly. Our research is a step towards making
cities smarter, more sustainable, and more enjoyable places to live by leveraging
the power of real-time data processing and intelligent optimization. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9188899
@misc{9188899,
abstract = {{Traffic congestion is a persistent problem in modern urban environments, causing
delays, increasing pollution, and negatively affecting the quality of life of millions
of city dwellers. As urban populations grow, the need for intelligent traffic man-
agement systems becomes more pressing. This thesis presents a novel approach
to real-time traffic management using edge computing in conjunction with the
Urban Mobility Simulation (SUMO) tool. The Differential Evolution (DE) algo-
rithm is applied to optimize traffic signal timings, with the goal of minimizing
vehicle delays at multiple intersections within a simulated smart city. Using edge
computing, traffic data is processed locally, enabling faster responses and dynamic
adjustments to signal timings. The results of this approach demonstrate a sig-
nificant improvement in traffic flow efficiency, with reductions in vehicle delays in
various traffic scenarios. This research highlights the potential for combining edge
computing with evolutionary algorithms to address traffic congestion challenges in
modern cities.}},
author = {{Xu, Chun}},
language = {{eng}},
note = {{Student Paper}},
title = {{Leveraging Edge Computing for Real-Time Traffic Management and Simulation with SUMO in Smart Cities}},
year = {{2025}},
}