Real-time traffic data has become a fundamental component in optimizing AI-powered traffic signal control systems. Byleveraging live sensor inputs, computer vision, and machine learning algorithms, modern traffic management systems dynamicallyadjust signals to enhance traffic flow, minimize congestion, and reduce emissions. This review explores the latest advancementsinAI-driven traffic control, focusing on real-time data integration and its effectiveness in adaptive signal optimization. Furthermore,the study highlights key challenges such as data reliability, computational overhead, and ethical considerations in AI trafficsystems. The findings suggest that AI-driven traffic signal control significantly improves urban mobility and sustainability, thoughfurther research is needed to address implementation challenges. Keywords: Real-time Traffic Data, AI-powered Traffic Signals, Intelligent Transportation Systems, Machine Learning, Urban Mobility Optimization