Intelligent management of mobile charging fleet with traffic prediction-based routing and emergency vehicle servicing

Rapid growth in electric vehicle adoption presents a critical challenge for sustainable urban development and power grid management, particularly in ensuring reliable charging under congested traffic conditions. The overlap between peak traffic hours and electricity demand surges often leads to long queues at charging stations, degraded service quality, and disruptions in grid stability. To address this issue, the present study proposes the deployment of mobile charging fleets as a means to alleviate congestion at fixed stations and mitigate stress on the power grid. However, urban traffic significantly affects the routing efficiency and economic performance of such fleets, while accurate traffic flow prediction remains a major challenge due to the complexity and time-series nature of traffic data. Furthermore, the growing number of EVs has intensified the need for effective emergency response, particularly in cases of battery depletion in remote areas. To overcome these challenges, this paper introduces a coordinated transportation system integrating the power distribution network with urban traffic infrastructure. By leveraging traffic models derived from graph neural networks, the proposed system enhances the performance of mobile charging fleets through adaptive routing and optimized energy exchange with EVs and the power grid, thereby enabling efficient emergency servicing.