Dynamic Traffic Optimization Through Cloud-Enabled Big Data Analytics and Machine Learning for Enhanced Urban Mobility

Addressing the critical problem of road traffic congestion that robs people of time, ruins the environment, and eats into the purse to the detriment of urban mobility, this paper. The research is relevant as urban congestion remains a serious issue currently, and for which new traffic management solutions for more efficient traffic management are needed. The intelligent traffic control system, developed via the integration of cloud computing, big data analytics and machine learning (using the RandomForest algorithm for predictive analysis) is the proposed solution. From sensors, GPS devices, and social networks, the system collects real time traffic data, and retime and reroute vehicles in accordance with current traffic conditions. Results show that the system can: increase safety in urban environments, reduce congestion, and improve traffic flow. The results indicated perfect classification accuracy by the RandomForest algorithm with accurate real time traffic prediction and effective management of traffic. It is concluded that cloud infrastructure integration results in scalability and flexibility that makes the infrastructure capable of handling large datasets. Some potential applications include a wide scale deployment in smart cities and future research can further enhance traffic safety and reduce travel time by further improving predictive models and using AI based decision making.