Enabling Sustainable E-Mobility: An Edge–Cloud Collaborative Framework for Lifecycle Health Management of Electric Vehicle Batteries

The rapid adoption of electric vehicles (EVs) is a cornerstone of the transition to sustainable transportation. However, uncertainty regarding battery degradation remains a significant obstacle, hindering vehicle energy efficiency, operational safety, and the recovery of end-of-life value. Accurate estimation of the battery state of health (SOH) and prediction of the remaining useful life (RUL) are therefore critical for sustainable vehicle lifecycle management. This study proposes an edge–cloud collaborative intelligent framework for in-vehicle deployment that leverages a Transformer-based architecture to jointly model SOH and RUL. The cloud-side model retains the full configuration to capture long-term degradation trajectories for high-accuracy RUL prediction. A lightweight edge-side model, engineered via pruning and knowledge distillation, delivers millisecond-level inference for real-time SOH estimation onboard the vehicle. To ensure efficiency, only four core health indicators are extracted for end-to-end prediction. Experimental validation across 77 battery cells demonstrates that the framework achieves SOH estimation with a root mean square error (RMSE) of 1.41%, and RUL prediction with an RMSE of 2.59% (78 cycles). Furthermore, a periodic cloud-side update and over-the-air deployment mechanism ensure long-term adaptability and cross-platform scalability without full local retraining. This intelligent prognostic framework directly enhances EV reliability and sustainability by providing health-informed decision support for optimal vehicle operation, maintenance scheduling, and the reuse of second-life batteries. Consequently, it serves as a vital tool for advancing resource optimization and circular economy principles within the E-mobility ecosystem.