In the rapidly evolving landscape of next-generation 6G systems, the integration of AI functions to orchestrate network resources and meet stringent user requirements is a key focus. Distributed Learning (DL), a promising set of techniques that shape the future of 6G communication systems, plays a pivotal role. Vehicular applications, representing various services, are likely to benefit significantly from the advances of 6G technologies, enabling dynamic management infused with inherent intelligence. However, the deployment of various DL methods in traditional vehicular settings with specific demands and resource constraints poses challenges. The emergence of distributed computing and communication resources, such as the edge-cloud continuum and integrated terrestrial and non-terrestrial networks (T/NTN), provides a solution. Efficiently harnessing these resources and simultaneously implementing diverse DL methods becomes crucial, and Network Slicing (NS) emerges as a valuable tool. This study delves into the analysis of DL methods suitable for vehicular environments alongside NS. Subsequently, we present a framework to facilitate DL-as-a-Service (DLaaS) on a distributed networking platform, empowering the proactive deployment of DL algorithms. This approach allows for the effective management of heterogeneous services with varying requirements. The proposed framework is exemplified through a detailed case study in a vehicular integrated T/NTN with diverse service demands from specific regions. Performance analysis highlights the advantages of the DLaaS approach, focusing on flexibility, performance enhancement, added intelligence, and increased user satisfaction in the considered T/NTN vehicular scenario.

With the advent of 6G technology, the proliferation of interconnected devices necessitates a robust, fully connected intelligence network. Federated Learning (FL) stands as a key distributed learning technique, showing promise in recent advancements. However, the integration of novel Internet of Things (IoT) applications and virtualization technologies has introduced diverse and heterogeneous devices into wireless networks. This diversity encompasses variations in computation, communication, storage resources, training data, and communication modes among connected nodes. In this context, our study presents a pivotal contribution by analyzing and implementing FL processes tailored for 6G standards. Our work defines a practical FL platform, employing Raspberry Pi devices and virtual machines as client nodes, with a Windows PC serving as a parameter server. We tackle the image classification challenge, implementing the FL model via PyTorch, augmented by the specialized FL library, Flower. Notably, our analysis delves into the impact of computational resources, data availability, and heating issues across heterogeneous device sets. Additionally, we address knowledge transfer and employ pre-trained networks in our FL performance evaluation. This research underscores the indispensable role of artificial intelligence in IoT scenarios within the 6G landscape, providing a comprehensive framework for FL implementation across diverse and heterogeneous devices.

With the widespread adoption of 5G as a communication standard, satellite mega-constellations have emerged as viable alternatives and complement terrestrial networks, offering extensive and reliable communication services across a broad spectrum of users and applications. These constellations are already equipped with inter-satellite links and adaptable payloads capable of supporting Radio Access Network (RAN) and core network functionalities, forming complex space-based networks characterized by overlapping layers of multi-orbit, grid-like topologies that undergo continuous, yet predictable, changes—peculiarities not currently addressed within the 5G standards framework. To cope with this technology gap, this paper introduces a novel architecture for 5G services relying on satellite mega-constellations, which adhere to the principles of self-organized networks. This architecture is designed to align seamlessly with 5G service requirements, while also accommodating the unique topological and infrastructural constraints of mega-constellations. In more detail, the paper first outlines the fundamental principles of self-organizing networks that facilitate real-time system adaptation to internal topological shifts and external fluctuations in service demand. Then, we detail a 5G network architecture incorporating these principles, which includes i) dynamic placement and migration of radio and core network control plane functions, ii) the strategic positioning of the data path, service, and AI decision functionalities to improve end-to-end service quality and reliability, and iii) the integration of dynamically established multi-connectivity options to increase the overall service dependability. These innovations aim for a seamless integration of space-based networks with terrestrial counterparts, creating a robust, cost-effective convergent telecommunication system.

The development of the 5G network and the transition to 6G has given rise to multiple challenges for ensuring high-quality and reliable network services. One of these main challenges is the emergent intelligent defined networks (IDN), designed to provide highly efficient connectivity, by merging artificial intelligence (AI) and networking concepts, to ensure distributed intelligence over the entire network. To this end, it will be necessary to develop and implement proper machine learning (ML) algorithms that take into account this new distributed nature of the network to represent increasingly dynamic, adaptable, scalable, and efficient systems. To be able to cope with more stringent service requirements, it is necessary to renew the ML approaches to make them more efficient and faster. Distributed learning (DL) approaches are shown to be effective in enabling the possibility of deploying intelligent nodes in a distributed network. Among several DL approaches, transfer learning (TL) is a valid technique to achieve the new objectives required by emerging networks. Through TL, it is possible to reuse ML models to solve new problems without having to recreate a learning model from scratch. TL, combined with distributed network scenarios, turns out to be one of the key technologies for the advent of this new era of distributed intelligence. The goal of this paper is to analyze TL performance in different networking scenarios through a proper MATLAB implementation.

This paper explores the practical implementation and performance analysis of distributed learning (DL) frameworks on various client platforms, responding to the dynamic landscape of 6G technology and the pressing need for a fully connected distributed intelligence network for Internet of Things (IoT) devices. The heterogeneous nature of clients and data presents challenges for effective federated learning (FL) techniques, prompting our exploration of federated transfer learning (FTL) on Raspberry Pi, Odroid, and virtual machine platforms. Our study provides a detailed examination of the design, implementation, and evaluation of the FTL framework, specifically adapted to the unique constraints of various IoT platforms. By measuring the accuracy of FTL across diverse clients, we reveal its superior performance over traditional FL, particularly in terms of faster training and higher accuracy, due to the use of transfer learning (TL). Real-world measurements further demonstrate improved resource efficiency with lower average load, memory usage, temperature, power, and energy consumption when FTL is implemented compared to FL. Our experiments also showcase FTL’s robustness in scenarios where users leave the server’s communication coverage, resulting in fewer clients and less data for training. This adaptability underscores the effectiveness of FTL in environments with limited data, clients, and resources, contributing valuable information to the intersection of edge computing and DL for the 6G IoT.

The successful integration of Terrestrial and Non-Terrestrial Networks (T/NTNs) in 6G is poised to revolutionize demanding domains like Earth Observation (EO) and Intelligent Transportation Systems (ITSs). Still, it requires Distributed Machine Learning (DML) frameworks that are scalable, private, and efficient. Existing methods, such as Federated Learning (FL) and Split Learning (SL), face critical limitations in terms of client computation burden and latency. To address these challenges, this paper proposes a novel hierarchical DML paradigm. We first introduce Federated Split Transfer Learning (FSTL), a foundational framework that synergizes FL, SL, and Transfer Learning (TL) to enable efficient, privacy-preserving learning within a single client group. We then extend this concept to the Generalized FSTL (GFSTL) framework, a scalable, multi-group architecture designed for complex and large-scale networks. GFSTL orchestrates parallel training across multiple client groups managed by intermediate servers (RSUs/HAPs) and aggregates them at a higher-level central server, significantly enhancing performance. We apply this framework to a unified T/NTN architecture that seamlessly integrates vehicular, aerial, and satellite assets, enabling advanced applications in 6G ITS and EO. Comprehensive simulations using the YOLOv5 model on the Cityscapes dataset validate our approach. The results show that GFSTL not only achieves faster convergence and higher detection accuracy but also substantially reduces communication overhead compared to baseline FL, and critically, both detection accuracy and end-to-end latency remain essentially invariant as the number of participating users grows, making GFSTL especially well suited for large-scale heterogeneous 6G ITS deployments. We also provide a formal latency decomposition and analysis that explains this scaling behavior. This work establishes GFSTL as a robust and practical solution for enabling the intelligent, connected, and resilient ecosystems required for next-generation transportation and environmental monitoring.