Using Federated Learning to Develop Congestion Control Solutions for Intelligent Transportation Systems
Journal of Internet Services and Applications · 31.07.2026 · 17 (1) · 327-340
DOI: 10.5753/jisa.2026.7087 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Internet Services and Applications, online erschienen am 31.07.2026. Verfasst von Carnot Braun und 2 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This article presents a comprehensive analysis of the application of Federated Learning (FL) to create congestion control and management solutions in the context of Intelligent Transportation Systems and Vehicular Networks. Starting from the types of communication in vehicular networks, which can be V2V, V2I, or V2X, the article presents three architectures for implementing federated learning in the context of connected vehicles: centralized, decentralized/hierarchical (using edge servers), and peer-to-peer architectures. Considering the variables available in vehicles that can be used to create congestion control solutions and how this information can be used in machine learning models, the article discusses the advantages and disadvantages of each architecture. Furthermore, the article presents data communication (V2V, V2I, and V2X) as a key element in the coordination of machine learning models and the possibilities for sharing information/models using the communication network. Finally, the article presents a case study illustrating traffic prediction with federated learning with a decentralized architecture composed of vehicles and edge servers in the network.
Zitieren
APA
Braun, C., Guidoni, D. L., & Souza, A. M. D. (2026). Using Federated Learning to Develop Congestion Control Solutions for Intelligent Transportation Systems. Journal of Internet Services and Applications, 17(1), 327-340. https://doi.org/10.5753/jisa.2026.7087
Vancouver
Braun C, Guidoni DL, Souza AMD. Using Federated Learning to Develop Congestion Control Solutions for Intelligent Transportation Systems. Journal of Internet Services and Applications. 2026;17(1):327-340. doi:10.5753/jisa.2026.7087
BibTeX
@article{Braun2026,
author = {Braun, Carnot and Guidoni, Daniel L. and Souza, Allan M. De},
title = {Using Federated Learning to Develop Congestion Control Solutions for Intelligent Transportation Systems},
journal = {Journal of Internet Services and Applications},
year = {2026},
volume = {17},
number = {1},
pages = {327--340},
doi = {10.5753/jisa.2026.7087}
}
EUVIMED