Proposing a framework for evaluating learning strategies in vehicular CPSs
Paper i proceeding, 2022

Highly-connected Vehicular Cyber-Physical Systems (VCPSs) offer manifold opportunities for distributing learning across the contained vehicles, road-side units and servers. However, simulating and evaluating particular distributed learning schemes poses a difficult problem in requiring realistic modeling of the vehicular fleet, communication, and the learning itself. In this work, we postulate a set of requirements for a framework simulating a complete learning workflow in a VCPS, and propose a modular architecture for it. Using a prototype implementation, we show with an example experiment the capabilities the proposed framework delivers for evaluating novel learning schemes in custom scenarios.

Fedrated learning

connected vehicle

Författare

Bastian Havers

Nätverk och System

Volvo Cars

Marina Papatriantafilou

Nätverk och System

Ashok Krishna Chaitanya Koppisetty

Volvo Cars

Vincenzo Massimiliano Gulisano

Nätverk och System

Middleware 2022 Industrial Track - Proceedings of the 23rd International Middleware Conference Industrial Track, Part of Middleware 2022

22-28
978-1-4503-9917-3 (ISBN)

23rd International Middleware Conference
Quebec City, Canada,

AutoSPADA (Automotive Stream Processing and Distributed Analytics) OODIDA Phase 2

VINNOVA (2019-05884), 2020-03-12 -- 2022-12-31.

Ämneskategorier

Annan data- och informationsvetenskap

Systemvetenskap

Datavetenskap (datalogi)

Styrkeområden

Informations- och kommunikationsteknik

Transport

DOI

10.1145/3564695.3564775

ISBN

9781450399173

Mer information

Senast uppdaterat

2023-10-27