Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services. Federated learning (FL) overcomes privacy constraints by training ML models in distributed systems, exchanging model parameters instead of raw data. However, the dynamic states of connected vehicles affect the network connection quality and influence the FL performance. To tackle this challenge, we propose a contextual client selection pipeline that uses Vehicle-to-Everything (V2X) messages to select clients based on the predicted communication latency. The pipeline includes: (i) fusing V2X messages, (ii) predicting future traffic topology, (iii) pre-clustering clients based on local data distribution similarity, and (iv) selecting clients with minimal latency for future model aggregation. Experiments show that our pipeline outperforms baselines on various datasets, particularly in noniid settings. I. I Machine learning (ML), a subfield of artificial intelligence, focuses on developing learning algorithms and inference models that enable digital systems to make decisions and predictions in terms of the knowledge learned from data. Over the past years, ML-based approaches exhibited great potential to revolutionize various scientific, engineering, economic, and cultural fields with outstanding technological advancements such as Google AlphaGo and Open AI's Chat-GPT. In the filed of road transportation, ML is possible to empower numerous new applications for realizing Intelligent Transportation System (ITS), e.g., environmental perception, road traffic flow optimization, and trajectory planning, which can significantly enhance the safety and efficiency of transportation systems [1]-[5]. Recently, a new ITS concept referred to as Cooperative Intelligent Transportation System (C-ITS) attacked a lot of interests from both academia and industry [6]. In C-ITS, the cooperation between two or more ITS sub-systems (personal, vehicle, roadside and central) offers better quality This work was supported by the German Federal Ministry for Digital and Transport (BMVI) in the projects "KIVI -KI im Verkehr Ingolstadt" and "5GoIng -5G Innovation Concept Ingolstadt".

No abstract

No abstract

A reliable and all-pervading information-sharing mechanism between traffic participants and infrastructure systems, widely termed V2X communication, is crucial to realize the goals of future cooperative intelligent transportation systems -that of improving traffic safety and efficiency. The need to maintain high reliability and availability amidst a permanentlychanging network topology caused by the moving vehicles translate into an increased demand for network management infrastructure and radio resources. Such capital-intensive demands can act as significant deterrents in the quest for a rapid large-scale deployment of V2X technologies. With the goal to reduce the demand for fixed infrastructure and radio resources, we propose an alternate network deployment architecture based on the concept of moving network convoys, deploy it in a distributed C-ITS simulation environment, and provide a quantitative assessment of the potential benefits in comparison to conventional network deployment architectures.

No abstract