Smartphone time-to-empty (TTE) estimation is vulnerable to residual battery-drain effects after short-duration user activities, which can cause runtime predictions to fluctuate. This paper proposes a continuous-time battery-drain model that separates instantaneous and delayed drain effects in operating-system logs. The discharge process is decomposed into baseline drain, direct drain induced by the current usage state, and delayed tail drain triggered by transient events. Multi-exponential recursive states are used to represent network communication, location requests, background wake-ups, and related events as residual drain terms that decay over time. Non-negative sparse estimation is adopted to preserve the interpretability of the individual contributions. Experiments are conducted on a public smartphone-log dataset with strict separation between the training and test sets. The results show that the proposed method achieves stable TTE prediction performance on the test set, with short-horizon values above 0.963 and scenario-level MAPE of 2.42–5.03%. These findings indicate that explicit modeling of delayed residual drain can improve the accuracy and stability of smartphone remaining-runtime prediction.
Accurate state-of-charge (SOC) prediction on personal mobile devices requires a model that can represent heterogeneous discharge mechanisms, transfer knowledge across users, and adapt from scarce target records while raw telemetry remains privacy isolated. This study proposes a module-decomposition-driven SOC prediction model that separates baseline drain, synchronous state response, and asynchronous multi-scale event memory within one discharge-dynamics formulation. The same three semantic coefficient blocks remain aligned through local source learning and round-wise sample-count-weighted federated aggregation. Target-side personalization then adjusts one locally derived personal discharge-rate scalar while preserving the shared temporal response, and forward SOC propagation produces threshold-based time-to-empty (TTE) estimates. A user-held-out evaluation on a public small-sample smartphone-log dataset uses eight target partitions and 447 final evaluation origins. Personalized fine-tuning reduced TTE MAE by 67.07% and RMSE by 71.88%, yielding an of 0.936. The resulting task-specific architecture connects module-structured data processing, federated synthesis, few-shot adaptation, and local TTE inference while raw usage logs remain within user-specific data boundaries.