Few-Shot Learning for Triplet-Based EV Energy Consumption Estimation

Predicting the energy consumption of an electric vehicle (EV) is often relevant when planning and managing electric mobility. The prediction is challenging as EV energy consumption is highly variable and dependent on context. First, this paper proposes an integrated framework for the collection of o...

Full description

Saved in:
Bibliographic Details
Main Authors: Alminas Čivilis, Linas Petkevičius, Simonas Šaltenis, Kristian Torp, Ieva Markucevičiūtė-Vinckė
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Applied Artificial Intelligence
Online Access:https://www.tandfonline.com/doi/10.1080/08839514.2025.2474785
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849393706342285312
author Alminas Čivilis
Linas Petkevičius
Simonas Šaltenis
Kristian Torp
Ieva Markucevičiūtė-Vinckė
author_facet Alminas Čivilis
Linas Petkevičius
Simonas Šaltenis
Kristian Torp
Ieva Markucevičiūtė-Vinckė
author_sort Alminas Čivilis
collection DOAJ
description Predicting the energy consumption of an electric vehicle (EV) is often relevant when planning and managing electric mobility. The prediction is challenging as EV energy consumption is highly variable and dependent on context. First, this paper proposes an integrated framework for the collection of online telematic data, processing of this data, online maintenance of statistics, and machine-learning-based prediction of travel time and energy consumption. A key feature of the proposed framework is the preprocessing of the trajectory data into triplets, a convenient data unit that captures the relevant context necessary for effective energ y prediction. The second contribution of the paper addresses the effective management of drastic change in context through robust energy prediction models. In particular, using few-shot learning techniques, we tackle the problem of the need to create different energy prediction models for different EV types, from small EVs to electric buses. Experimental results on three different data sets demonstrate how energy prediction models adapt to different EV types.
format Article
id doaj-art-4238ab7fbfa74bc49fa3f54dde3e2c8c
institution Kabale University
issn 0883-9514
1087-6545
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Applied Artificial Intelligence
spelling doaj-art-4238ab7fbfa74bc49fa3f54dde3e2c8c2025-08-20T03:40:21ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452025-12-0139110.1080/08839514.2025.2474785Few-Shot Learning for Triplet-Based EV Energy Consumption EstimationAlminas Čivilis0Linas Petkevičius1Simonas Šaltenis2Kristian Torp3Ieva Markucevičiūtė-Vinckė4Institute of Computer Science, Vilnius University, Vilnius, LithuaniaInstitute of Computer Science, Vilnius University, Vilnius, LithuaniaInstitute of Computer Science, Vilnius University, Vilnius, LithuaniaDepartment of Computer Science, Aalborg University, Aalborg, DenmarkNormalis Tech, Vilnius, LithuaniaPredicting the energy consumption of an electric vehicle (EV) is often relevant when planning and managing electric mobility. The prediction is challenging as EV energy consumption is highly variable and dependent on context. First, this paper proposes an integrated framework for the collection of online telematic data, processing of this data, online maintenance of statistics, and machine-learning-based prediction of travel time and energy consumption. A key feature of the proposed framework is the preprocessing of the trajectory data into triplets, a convenient data unit that captures the relevant context necessary for effective energ y prediction. The second contribution of the paper addresses the effective management of drastic change in context through robust energy prediction models. In particular, using few-shot learning techniques, we tackle the problem of the need to create different energy prediction models for different EV types, from small EVs to electric buses. Experimental results on three different data sets demonstrate how energy prediction models adapt to different EV types.https://www.tandfonline.com/doi/10.1080/08839514.2025.2474785
spellingShingle Alminas Čivilis
Linas Petkevičius
Simonas Šaltenis
Kristian Torp
Ieva Markucevičiūtė-Vinckė
Few-Shot Learning for Triplet-Based EV Energy Consumption Estimation
Applied Artificial Intelligence
title Few-Shot Learning for Triplet-Based EV Energy Consumption Estimation
title_full Few-Shot Learning for Triplet-Based EV Energy Consumption Estimation
title_fullStr Few-Shot Learning for Triplet-Based EV Energy Consumption Estimation
title_full_unstemmed Few-Shot Learning for Triplet-Based EV Energy Consumption Estimation
title_short Few-Shot Learning for Triplet-Based EV Energy Consumption Estimation
title_sort few shot learning for triplet based ev energy consumption estimation
url https://www.tandfonline.com/doi/10.1080/08839514.2025.2474785
work_keys_str_mv AT alminascivilis fewshotlearningfortripletbasedevenergyconsumptionestimation
AT linaspetkevicius fewshotlearningfortripletbasedevenergyconsumptionestimation
AT simonassaltenis fewshotlearningfortripletbasedevenergyconsumptionestimation
AT kristiantorp fewshotlearningfortripletbasedevenergyconsumptionestimation
AT ievamarkuceviciutevincke fewshotlearningfortripletbasedevenergyconsumptionestimation