This research study suggests a novel architecture for an Intelligent Network Management system to optimize urban traffic capacity for intelligent cities. The ever-increasing issue of traffic congestion in urban cities must evolve from conventional traffic management systems to information-based, more responsive systems. Our study suggests a centralized architecture making traffic control decisions based on real-time information from an IoT sensor network. The paper presents the design and simulation of the pick system within a controlled virtual environment. We experimented with the 'UrbanSim Traffic Dataset v2.0', a simulated dataset, to analyse traffic flows in a medium-sized city over 30 days. Data processing and simulation were both performed using MATLAB for basic algorithm development and SUMO (Simulation of Urban Mobility) to simulate an actual traffic scenario. The system, as demonstrated through simulation, exhibits a significant decrease in mean vehicle delay and an increase in mean speed compared to conventional traffic light-timing models. Our results demonstrate that real-time data analysis and dynamic traffic signal control can play a crucial role in alleviating traffic congestion, thereby reducing travel time, fuel consumption, and greenhouse gas emissions. This report covers system architecture, the approach used, simulation output, and the impact on future city development and smart city planning.
Vahora et al. (Tue,) studied this question.