Global urbanisation at an unprecedented rate has put increasing strain on city infrastructure, especially in the areas of environmental sustainability, traffic control, and transit. The needs of low-latency data processing and real-time decision-making necessary for effective urban mobility are becoming more and more difficult for traditional centralised computing models to handle. This paper presents an intelligent edge computing framework created especially to handle the intricacies of sustainable urban transport systems in response to these difficulties. A distributed network of AI-enabled edge nodes is used in the suggested architecture, and these nodes are placed strategically at important traffic locations including junctions, transit hubs, and emission-prone areas. These nodes can locally analyse data from a variety of sensors, such as traffic cameras, vehicle GPS systems, environmental monitors, and public transportation feeds, since they are outfitted with real-time processing capabilities. Without requiring continuous cloud connectivity, adaptive traffic light control, congestion forecasting, dynamic route optimisation, and proactive emissions management are made possible by the integration of machine learning algorithms at the edge.
Virendra Pratap Singh (Fri,) studied this question.