• A data-driven framework merges IoT, edge, and local analytics for EV fleets. • Machine learning forecasts battery health to guide energy-aware operations. • Hybrid BiLSTM–GRU and TabNet–TCN models enhance accuracy and scalability. • The system improves energy efficiency and stabilizes maintenance planning. • It bridges technical forecasting with strategic fleet-management insights. Efficient energy and asset management is a key economic driver in the large-scale deployment of electric vehicles (EVs). This research develops a data‑driven management framework that integrates Internet-of-Things (IoT) connectivity, edge computing, and on-premises analytics to forecast battery state-of-health (SOH) and optimize lifecycle performance in EV fleets. The proposed multilayered architecture establishes a closed decision-support loop combining localized intelligence for rapid diagnostics with centralized analytics for long-term strategic optimization. Machine-learning models—including BiLSTM–GRU and TabNet–TCN hybrids—are employed within an operational context to balance prediction accuracy, computational cost, and system scalability. Validation using the NASA PCoE lithium-ion dataset confirms that this integrated approach enhances energy-use efficiency and reduces maintenance cost variability under real-world uncertainty. In addition, connecting battery health forecasting to broader economic considerations reinforces effective management strategies, supporting cost–efficient and sustainable decision–making in real EV operations. By linking technical forecasting with managerial decision insights, the framework supports sustainable fleet operation, strengthens predictive maintenance planning, and aligns with UN SDG 7 objectives on affordable and clean energy. This study therefore bridges the technical and managerial perspectives of energy conversion and management, demonstrating how intelligent analytics can inform effective decision-making in EV-based energy ecosystems.
Ji et al. (Sun,) studied this question.