With the global transportation sector being a major contributor to greenhouse gas (GHG) emissions, transitioning to cleaner and more efficient forms of transportation is essential for mitigating climate change and improving air quality. Toward sustainable mobility, Fuel Cell Electric Vehicles (FCEVs) have emerged as a promising solution offering zero-emission transportation without sacrificing performance or range. However, FCEV adoption still faces significant challenges regarding refueling infrastructure. This work proposes an innovative refueling automation service for FCEVs to facilitate the refueling procedure and to increase the fuel cell lifetime, by leveraging (i) Big Data, namely, real-time mobility data and (ii) Machine Learning (ML) for the energy consumption forecasting to dynamically adjust refueling priorities. The proposed service was evaluated on a simulated FCEV energy consumption dataset, generated using both the Future Automotive Systems Technology Simulator and real-time data, including traffic information and details from a real-world on demand Public Transportation service in the Geneva Canton region. The experimental results showcased that all three ML algorithms achieved high accuracy in forecasting the vehicle’s energy consumption with very low errors on the order of 10% and below 20% for the normalized Mean Absolute Error and normalized Root Mean Squared Error metrics, respectively, indicating the high potential of the suggested service.