Federated Computing in Electric Vehicles to Predict Coolant Temperature

René Schwermer, Ekin Alp Bicer, Pascal Schirmer, Ruben Mayer, Hans Arno Jacobsen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Reducing greenhouse gas emissions in mobility is paramount to achieving a carbon-neutral society. However, battery-electrical vehicles (BEV) introduce unique engineering challenges to protect expensive electrical components from overheating. A centralized architecture for model-driven predictions of coolant temperatures poses privacy and legal issues. Additionally, the applications in a vehicle compete for the available resources and must use them as sparingly as possible. Therefore, we introduce a new federated computing (FC) use case to help transform the mobility sector. We evaluate the performance of two FC approaches (linear regression and machine learning) on hardware and privacy metrics by leveraging a real-world dataset from BEVs. Our findings show trade-offs between hardware utilization and model accuracy. The linear regression model yields the best performance and prediction metrics. FC with ML shows up to 761 % variances when comparing vehicle-specific models with models trained with the entire fleet and clustering the data into velocity profiles partly improves prediction performance.

Original languageEnglish
Title of host publicationMiddleware Industrial Track 2023 - Proceedings of the 2023 24th International Middleware Conference Industrial Track, Part of
Subtitle of host publicationMiddleware2023
PublisherAssociation for Computing Machinery, Inc
Pages8-14
Number of pages7
ISBN (Electronic)9798400704277
DOIs
StatePublished - 11 Dec 2023
Externally publishedYes
Event24th International Middleware Conference Industrial Track, Middleware Industrial Track 2023 - Bologna, Italy
Duration: 11 Dec 202315 Dec 2023

Publication series

NameMiddleware Industrial Track 2023 - Proceedings of the 2023 24th International Middleware Conference Industrial Track, Part of: Middleware2023

Conference

Conference24th International Middleware Conference Industrial Track, Middleware Industrial Track 2023
Country/TerritoryItaly
CityBologna
Period11/12/2315/12/23

Keywords

  • Electric Vehicle
  • Federated Computing
  • Systems

Fingerprint

Dive into the research topics of 'Federated Computing in Electric Vehicles to Predict Coolant Temperature'. Together they form a unique fingerprint.

Cite this