Real Time Traffic Congestion Prediction in Smart Cities

Abstract

Morning traffic congestions are a frequent problem for students travelling to college, often causing delays and affects punctuality. Based on a review of studies in traffic congestion prediction, intelligent transportation systems, IoT-enabled traffic monitoring, and AI-based route optimization, this work is a realtime traffic monitoring and route suggestion system customised for students. The system will take three inputs - starting location, destination, and planned departure time - and will use live traffic data to assess all possible routes. Each route will be classified as having light, moderate, or heavy traffic, and the system will also predict traffic conditions for the chosen departure time using the past patterns. It will suggest the most suitable time to start the journey and provide a ‘late arrival risk’ score based on class start times. Additionally, a crowd feedback feature will allow students to report unusual travel issues such as campus gate congestion, road closures, or strikes, ensuring more accurate and relevant travel information. The system will also be designed to send alerts through SMS, WhatsApp, or push notifications when heavy traffic is expected in future. Once implemented, it is expected to help students plan their trips more effectively, reduce delays, save travel time, and improve punctuality while promoting more efficient urban transportation.