Problem
Research questions and friction points this paper is trying to address.
battery power prediction
distribution shift
model adaptation
electric vehicles
on-device learning
On-Device Adaptive Battery Power Prediction for Electric Vehicles
🤖 AI Summary
This study addresses the significant performance degradation of electric vehicle battery power prediction models when confronted with distribution-shifted data, which hinders their applicability in real-world adaptive power management. To overcome this limitation, the authors propose a novel approach that transforms pretrained time series forecasting models into adaptive variants capable of efficient online and offline continual learning on resource-constrained onboard devices, while preserving critical prior knowledge. The method consistently outperforms static deployment strategies across diverse model architectures and prediction horizons, achieving substantial improvements in prediction accuracy—reducing mean absolute error by 7.49% in online settings and 14.88% in offline scenarios.
📝 Abstract
Adaptive power management in Electric Vehicles (EVs) requires accurate power prediction. Although deep learning models have emerged as highly effective for time-series forecasting in this domain, their performance is prone to degradation when exposed to data with distributions different from the training data. We introduce a novel approach that enables on-device learning in resource-constrained EV systems to continuously adapt pretrained battery prediction models to new, unseen data. We leverage existing pretrained models by transforming them into adaptable versions that retain critical hyperparameter knowledge from their initial training. We comprehensively investigate both online and offline model adaptation strategies. Our results demonstrate significant improvements in forecasting performance across various models and time horizons, achieving mean absolute error reductions of up to 7.49\% and 14.88\% with online and offline adaptation techniques, respectively. This study highlights the substantial benefit of on-device adaptation, resulting in enhanced battery power predictions than unadapted model deployments in real-world EV scenarios.
Innovation
Methods, ideas, or system contributions that make the work stand out.
on-device learning
adaptive power prediction
battery forecasting
distribution shift adaptation
electric vehicles
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
