A Simulation-based Decision Support System for Urban Traffic Management

One common challenge faced by smart cities is traffic congestion, caused also unintentionally by city planners, which significantly impacts urban life and the environment. To address these issues, various strategies and approaches are explored, including advanced traffic management methods, communication systems, and predictive modeling. In this study, we introduce a Digital Twin decision support system that focuses on accurately modeling a city's road network and replicating traffic patterns for specific time frames. Central to this project is SUMO, a microscopic vehicular traffic simulator used to create the reference road model. Our research presents a flexible and viable methodology for generating SUMO-compliant simulations that leverage real vehicular data from the city to analyze urban traffic and its conditions. To illustrate our approach, we apply it to a specific case study centered on examining environmental emissions in the city of Bologna, Italy. This approach shows promise in enhancing traffic management and overall urban efficiency within the broader context of smart cities.