IoT-Simulated Digital Twin with AI Traffic Signal Control for Real-Time Traffic Optimization in SUMO

Area of Science:

• Intelligent Transportation Systems
• Artificial Intelligence in Urban Planning
• Internet of Things Applications

Background:

• Urban traffic congestion causes significant delays, economic losses, and environmental pollution.
• Real-time traffic data from the Internet of Things (IoT) is available, but testing new control strategies live is risky and expensive.
• Existing traffic control methods like fixed-time and vehicle-actuated systems have limitations in optimizing traffic flow.

Purpose of the Study:

• To propose and evaluate an IoT-driven digital twin framework for designing and testing AI-based traffic management systems.
• To create a safe, cost-effective, and scalable simulation environment for intelligent traffic control strategies.
• To demonstrate the efficacy of AI agents in real-time traffic signal adaptation.

Main Methods:

• Developed an IoT-driven digital twin using the Simulation of Urban MObility (SUMO) platform and its Python API.
• Emulated a dense network of IoT sensors to stream real-time traffic data (vehicle density, queue lengths, waiting times).
• Trained an AI agent with a composite reward function to minimize waiting times and emissions, controlling traffic signals adaptively.

Main Results:

• The AI-controlled system demonstrated superior performance compared to fixed-time and vehicle-actuated controls under various traffic demands.
• The digital twin framework successfully simulated real-time traffic data and AI-driven signal adaptation.
• The approach proved effective in jointly minimizing vehicle waiting times and emissions.

Conclusions:

• Combining IoT-based simulation with AI control offers a viable and safe method for developing intelligent traffic management systems.
• The proposed digital twin framework provides a scalable pathway for the real-world deployment of advanced traffic solutions.
• This research highlights the potential of AI and IoT to create more efficient and sustainable urban transportation networks.