[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82333-en":3,"doc-seo-82333-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82333,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","On-Device Adaptive Battery Power Prediction for Electric Vehicles","Adaptive power management in electric vehicles requires reliable battery power forecasting that remains accurate under shifting real-world data distributions. The study proposes on-device learning that continuously adapts pretrained battery prediction models to new, unseen inputs in resource-constrained vehicle systems. Pretrained models are transformed into adaptable variants while preserving key hyperparameter knowledge. Online and offline adaptation strategies are evaluated, showing mean absolute error reductions up to 7.49% (online) and 14.88% (offline) across models and time horizons, outperforming non-adapted deployments.","On-Device Adaptive Battery Power Prediction for  \nElectric Vehicles  \nAvik Bhatnagar, Anton Paule, Tobias Schuermann, Sebastian Reiter, Oliver Bringmann  \nFZI Research Center for Information Technology, University of T u¨bingen  \nGermany  \n[bhatnagar@fzi.de](bhatnagar@fzi.de), [paule@fzi.de](paule@fzi.de), [schuermann@fzi.de](schuermann@fzi.de), [reiter@fzi.de](reiter@fzi.de), [oliver.bringmann@uni-tuebingen.de](oliver.bringmann@uni-tuebingen.de)  \narXiv :2607 .09400v 1 [ cs .LG] 10 Jul 2026  \nAbstract—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 ondevice 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.  \nKeywords—Time-series forecasting, Deep learning, Data distribution shift, Model adaptation, On-device learning, Resourceconstrained systems.  \nI. INTRODUCTION  \nTime-series signals, which are ubiquitous in daily life, are data recorded at regular intervals. Examples include financial market data, environmental measurements, and medical sensor data. Analyzing historical values to predict future trends offers significant benefits for proactive planning, operational optimization, and risk management. Advancements in deep learning have popularized its techniques for time-series forecasting applications [1] . Architectures such as Multi-layer Perceptrons (MLP), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) demonstrate superior accuracy in future value prediction compared to conventional statistical methods [2] . These neural networks implicitly learn temporal features from input signals and predict single or multiple future time steps from the previous time steps [3] .  \nDeep learning techniques have also been successfully applied in time series forecasting for Electric Vehicles (EVs), including predicting charging demand [4]–[6], estimating the battery State of Charge (SOC) and residual capacity [7], [8] . Our study extends the application of deep learning to the instantaneous battery power prediction. While existing studies  \nThis research was funded by the German Federal Ministry of Research, Technology and Space (BMFTR) as part of the project KI4BoardNet under Grant 16ME0778 .  \ncover forecasting granularities from minutes to months, we predicted future battery power consumption values for a very short-term horizon (1–3 seconds) using deep-learning models. This proactive prediction can support Battery Management System (BMS) operations, optimize the vehicle battery power supply, and prevent sudden power surge or drop peaks through load management schemes [9] .  \nHowever, practical battery power prediction faces challenges due to dynamically changing data distributions. Environmental factors (e.g., weather and elevation) and user behavior significantly influence the electrical power demand of EVs [10] . Driver actions, particularly driving style, directly impact the overall electrical power requirements for the propulsion and auxiliary systems. Aggressive acceleration ","cbCails3xzBqrMen","https://ap.wps.com/l/cbCails3xzBqrMen","pdf",562690,1,6,"English","en",105,"# Introduction\n## Time-series forecasting background\n## EV battery power forecasting and challenges\n## Continual learning approaches for time series\n## Motivation and study contribution","[{\"question\":\"Why do deep learning battery power prediction models degrade in electric vehicles?\",\"answer\":\"Their performance drops when the incoming data distribution differs from the training distribution, which is common due to changing environmental conditions and user driving behavior.\"},{\"question\":\"How does the proposed method enable adaptation on resource-constrained EV hardware?\",\"answer\":\"It transforms existing pretrained battery prediction models into adaptable versions and performs continuous learning via real-time inference and on-device updates.\"},{\"question\":\"What accuracy gains does online and offline adaptation achieve?\",\"answer\":\"Experiments report mean absolute error reductions up to 7.49% with online adaptation and up to 14.88% with offline adaptation across various models and short time horizons.\"}]",1784179707,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"on-device-adaptive-battery-power-prediction-for-electric-vehicles","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/on-device-adaptive-battery-power-prediction-for-electric-vehicles/82333/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why do deep learning battery power prediction models degrade in electric vehicles?","Question",{"text":74,"@type":75},"Their performance drops when the incoming data distribution differs from the training distribution, which is common due to changing environmental conditions and user driving behavior.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed method enable adaptation on resource-constrained EV hardware?",{"text":79,"@type":75},"It transforms existing pretrained battery prediction models into adaptable versions and performs continuous learning via real-time inference and on-device updates.",{"name":81,"@type":72,"acceptedAnswer":82},"What accuracy gains does online and offline adaptation achieve?",{"text":83,"@type":75},"Experiments report mean absolute error reductions up to 7.49% with online adaptation and up to 14.88% with offline adaptation across various models and short time horizons.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]