Integrated simulation and optimisation of traffic flow management systems in urban smart cities

Abstract

Traffic congestion in urban areas is a significant challenge for smart city management. This study aims to integrate SUMO software-based simulation and the Ant Colony Optimization (ACO) algorithm to improve traffic management efficiency. The simulation model maps vehicle flow on a road network in an urban area with high congestion. At the same time, the ACO algorithm is used to optimize traffic light settings and vehicle routes dynamically. The data includes travel time, fuel consumption, carbon emissions, and road congestion. The results show that traffic optimization reduces the average travel time from 35 minutes to 25 minutes (a reduction of 28.57%) and fuel consumption from 0.12 litres/km to 0.09 litres/km (a saving of 25%). In addition, vehicle carbon emissions are reduced from 450 g CO₂/km to 360 g CO₂/km (a reduction of 20%). The even distribution of vehicle flow also reduces congestion levels on main roads by 30%. Although the results are promising, real-world implementation faces technical obstacles, such as the need for IoT infrastructure and non-technical barriers, such as public resistance to changes in traffic policies. This study proves that an integrated simulation and optimization approach can effectively overcome congestion in smart cities while supporting environmental sustainability and transportation efficiency. Further research is recommended to develop more adaptive algorithms and test implementations in regions with different traffic characteristics.