Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning

In this work, an extension of the federated averaging algorithm, FedAvg-Gaussian, is applied to train probabilistic neural networks. The performance advantage of probabilistic prediction models is demonstrated and it is shown that federated learning can improve driving range prediction. Using probab...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Autor principal: Thorgeirsson, Adam Thor
Formato: Online
Idioma:inglês
Publicado em: KIT Scientific Publishing 2024
Assuntos:
Acesso em linha:https://library.oapen.org/handle/20.500.12657/93282
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
_version_ 1869516402834014208
author Thorgeirsson, Adam Thor
author_browse Thorgeirsson, Adam Thor
author_facet Thorgeirsson, Adam Thor
author_sort Thorgeirsson, Adam Thor
collection Directory of Open Access Books
description In this work, an extension of the federated averaging algorithm, FedAvg-Gaussian, is applied to train probabilistic neural networks. The performance advantage of probabilistic prediction models is demonstrated and it is shown that federated learning can improve driving range prediction. Using probabilistic predictions, routing and charge planning based on destination attainability can be applied. Furthermore, it is shown that probabilistic predictions lead to reduced travel time.
format Online
id doab-20.500.12854ir-145317
institution Directory of Open Access Books
language eng
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher KIT Scientific Publishing
publisherStr KIT Scientific Publishing
record_format ojs
spelling doab-20.500.12854ir-1453172025-05-27T06:49:46Z Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning Thorgeirsson, Adam Thor Reichweite; Federated Learning; Probabilistic Predictions; Driving Range; Electric Vehicles; Föderiertes Lernen; Probabilistische Vorhersage; Elektrofahrzeuge thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials In this work, an extension of the federated averaging algorithm, FedAvg-Gaussian, is applied to train probabilistic neural networks. The performance advantage of probabilistic prediction models is demonstrated and it is shown that federated learning can improve driving range prediction. Using probabilistic predictions, routing and charge planning based on destination attainability can be applied. Furthermore, it is shown that probabilistic predictions lead to reduced travel time. 2024-09-17T04:32:56Z 2024-09-17T04:32:56Z 2024-09-16T10:02:59Z 2024 book https://library.oapen.org/handle/20.500.12657/93282 9783731513711 https://directory.doabooks.org/handle/20.500.12854/145317 eng Karlsruher Schriftenreihe Fahrzeugsystemtechnik open access image/jpeg image/jpeg image/jpeg image/jpeg Attribution 4.0 International Attribution 4.0 International Attribution 4.0 International Attribution 4.0 International https://library.oapen.org/bitstream/20.500.12657/93282/1/probabilistic-prediction-of-energy-demand-and-driving-range-for-electric-vehicles-with-federated-learning.pdf https://library.oapen.org/bitstream/20.500.12657/93282/1/probabilistic-prediction-of-energy-demand-and-driving-range-for-electric-vehicles-with-federated-learning.pdf https://library.oapen.org/bitstream/20.500.12657/93282/1/probabilistic-prediction-of-energy-demand-and-driving-range-for-electric-vehicles-with-federated-learning.pdf https://library.oapen.org/bitstream/20.500.12657/93282/1/probabilistic-prediction-of-energy-demand-and-driving-range-for-electric-vehicles-with-federated-learning.pdf KIT Scientific Publishing 10.5445/KSP/1000171796 10.5445/KSP/1000171796 68fffc18-8f7b-44fa-ac7e-0b7d7d979bd2 9783731513711 AG Universitätsverlage 190 open access
spellingShingle Reichweite; Federated Learning; Probabilistic Predictions; Driving Range; Electric Vehicles; Föderiertes Lernen; Probabilistische Vorhersage; Elektrofahrzeuge
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials
Thorgeirsson, Adam Thor
Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning
title Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning
title_full Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning
title_fullStr Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning
title_full_unstemmed Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning
title_short Probabilistic Prediction of Energy Demand and Driving Range for Electric Vehicles with Federated Learning
title_sort probabilistic prediction of energy demand and driving range for electric vehicles with federated learning
topic Reichweite; Federated Learning; Probabilistic Predictions; Driving Range; Electric Vehicles; Föderiertes Lernen; Probabilistische Vorhersage; Elektrofahrzeuge
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials
topic_facet Reichweite; Federated Learning; Probabilistic Predictions; Driving Range; Electric Vehicles; Föderiertes Lernen; Probabilistische Vorhersage; Elektrofahrzeuge
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TG Mechanical engineering and materials
url https://library.oapen.org/handle/20.500.12657/93282
work_keys_str_mv AT thorgeirssonadamthor probabilisticpredictionofenergydemandanddrivingrangeforelectricvehicleswithfederatedlearning