Urban traffic congestion presents a major challenge worldwide, adversely affecting both environmental conditions and the economy. This paper introduces an intelligent traffic management system that employs the Internet of Things (IoT), cloud computing, and edge computing to enhance traffic flow and alleviate congestion. The system implements a network of IoT sensors installed at intersections to gather real-time traffic information, such as vehicle density, speed, and queue length. This information is processed and analyzed using sophisticated machine learning algorithms at the edge, facilitating quick decision-making and flexible traffic signal management. The edge devices also filter and consolidate data before transmitting it to the cloud for additional analysis and the identification of long-term trends. This hybrid model merges the low-latency advantages of edge computing with the high computational capabilities of the cloud, yielding a more effective and responsive traffic management system. By optimizing traffic flow and mitigating congestion, this system could enhance air quality, decrease fuel consumption, and improve overall urban mobility.