CN+: Vehicular Dataset at Traffic Light Regulated Intersection in Bremen, Germany

Area of Science:

• Computer Science
• Transportation Engineering
• Network Engineering

Background:

• Vehicular Ad-Hoc Networks (VANETs) aim to improve road safety through vehicle-to-vehicle (V2V) communication.
• Real-world testing of VANET safety algorithms is costly and impractical.
• Simulation-based testing is a common alternative, but requires realistic data.

Purpose of the Study:

• To introduce a novel dataset, CN+, for enhancing VANET simulations.
• To provide realistic traffic data for testing safety algorithms.
• To bridge the gap between simulation and real-world VANET performance.

Main Methods:

• Collected data from over 25,000 vehicles over 32 hours.
• Focused data collection at a signalized intersection in Bremen, Germany.
• Developed the 'CN+' dataset for use in VANET simulations.

Main Results:

• The CN+ dataset offers a rich source of real-world traffic data.
• The dataset enables more accurate and realistic simulation of VANET scenarios.
• Facilitates improved validation of safety algorithms in a simulated environment.

Conclusions:

• The CN+ dataset is a valuable resource for VANET research.
• Utilizing real-world datasets in simulations significantly improves accuracy.
• This work supports the development of more effective vehicular safety systems.