Quantum Inspired Swarm Intelligence for Real Time Adaptive Traffic Signal Control in Urban Transportation Networks

Traffic congestion in the city is one of the most enduring problems in contemporary transport system and it may increase delays in travelling, fuel usage, and environmental degradation. In a bid to solve this problem, this paper presents a Quantum-Inspired Swarm Adaptive Traffic Control (QIS-ATC) model that can be used to optimize real-time signals in a network of intersections. The model will be the integration of the exploratory strength of quantum-inspired computation and the adaptative coordination of swarm intelligence to adapt traffic signal phases dynamically and data-driven based on the dynamic vehicle densities. The suggested QIS-ATC algorithm is applied and tested using a wide range of MATLAB simulations and compared to five available methods such as Fixed Time Control (FTC), Adaptive Control (AC), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO). The results of the experiments show that, QIS-ATC results in a 30-45 percent increase in the total efficiency of traffic flows, 20-35 percent in the reduction of the mean value of a waiting time and a significant decrease in the queue sizes, in comparison with the current techniques. Moreover, the model has quicker convergence and constant green phase assignment and optimized throughput across intersections. These findings underscore the prospects of QIS-ATC as a scalable and smart control system to smart city infrastructures where adaptive and sustainable traffic control is critical to enhancing mobility in the city and congestion alleviation.