Analysis on Advancements in Adaptive Traffic Lights System

Rapid urbanization and population increase have caused a dramatic growth in vehicular traffic, resulting in huge congestion at city intersections. This paper gives a comprehensive review of improvements in Adaptive Traffic Lights System (ATLS), which might be vital in developing Intelligent Transportation Systems (ITS). We examine numerous methodologies, together with machine learning, Internet of Things (IoT) integration, and fuzzy logic approaches, that have been applied to enhance traffic signal control to elevate the traffic flow at both single intersection or across network of intersection. These approaches are evaluated by using simulation tools like SUMO that show how some algorithm impacts the overall traffic condition. We compare key performance metrics for various RL and DRL based methods, which includes Average Queue Length (AQL), Average Waiting Time (AWT), and Average Travel Time (ATT). Our findings suggest that adaptive systems can lessen AQL by as much as 30%, decrease AWT by about 25%, and enhance ATT by 20% and improve vehicle throughput by 15% while also decreasing fuel consumption and CO2 emissions in comparison to traditional traffic light systems. This paper emphasizes the need for innovative ATLS solutions that leverage real-time information to optimize traffic flow and mitigate congestion effectively.