Today, an unprecedented number of researchers and companies are interested in exploring advanced and optimized protocols and algorithms making the 5G New Radio technology (and of course its evolutions) able to support different services under heterogeneous scenarios. In most cases, their studies leverage computer simulations and simple datasets describing isolated functionalities of the overall complex mobile communication system. Accordingly, despite all these valuable and available tools, there remains a lack of comprehensive, high-quality datasets that can support in-depth analysis, modeling, and testing of the 5G New Radio in real-world deployments. To bridge this gap, this paper presents a 5G dataset for Quality of Experience assessment in the new RAdio (5G-QoERA). Focusing the attention on a video streaming use case, the goal of the dataset is to indicate the level of quality experienced by mobile end users in terms of Mean Opinion Score, while jointly considering several influencing aspects such as real user mobility traces, real-world base station deployments and related radio map environments, variable scheduling decisions, and application-level details. After detailing the generation process of the dataset, a preliminary analysis of its features is conducted to underline the possible research activities that can take advantage of its usage.

The emergence of 6G networks demands environment-aware communication paradigms to ensure reliable and efficient connectivity, and Channel Knowledge Maps (CKMs) offer a promising solution by mapping spatial locations to detailed channel characteristics for proactive network optimization. In this context, this paper proposes an explainable Machine Learning (ML)-based framework that uses geometrical features to predict receiver state probabilities in UAV-based mmWave communication networks. Geometrical characteristics extracted from the environment surrounding each receiver are used to train ML models, namely Decision Tree (DT), K-Nearest Neighbors (KNN), and Deep Neural Network (DNN) models, to predict three receiver states probabilities: Line-of-Sight (LOS), No-Line-of-Sight (NLOS), and Blocked. Experimental results show that the DNN model outperforms DT and KNN, achieving higher accuracy across all states, albeit with no inherent explainability. To address this, the SHapley Additive exPlanations (SHAP) method is applied to indicate feature contributions to each state prediction of the black-box DNN model. This improves the interpretability and reliability of the proposed environment-aware framework for$\mathbf{6 G}$UAV-based networks.

In the era of pervasive connectivity, the effective provisioning of multimedia services surely represents a cornerstone challenge for both infrastructure and service providers. Given the recent evolution of Beyond 5G/6G networks, it is conventionally accepted that a Network Operator (infrastructure provider) shares its resources with tenants (service providers) by giving them the possibility to autonomously and efficiently configure the application services they provide to end users. To this end, this contribution proposes a cutting-edge framework for multimedia service provisioning, that harnesses the power of Artificial Intelligence (AI) in conjunction with Digital Twin Networks (DTNs). Specifically, it considers the real network features collected from the physical real network through Software-Defined Networking Controllers to build the DTN, whose purpose is to provide present and future physical, network, and application statistics through AI for efficient and proactive resource allocation. The DTN exposes to the tenant a concise set of monitoring parameters related to actual network-specific statistics and Quality of Service metrics and also future ones thanks to Deep Learning, without sharing in-depth details of the underlying network through Machine Learning (clustering). This information will be exploited by the service orchestrator for optimal resource allocation and redistribution, which will be deeply investigated in future works.

This paper describes the integration of Terrestrial and Non-Terrestrial Networks, wherein space-based network entities collaborate with traditional and emerging terrestrial communication frameworks to furnish pervasive, resilient, and three-dimensional wireless connectivity worldwide toward the 6th Generation of communication networks. This integration supports heterogeneous services, such as enhancing coverage, user experience, system capacity, service reliability, and availability, while also providing high-speed connectivity in remote or disaster-affected areas, improving existing 5th Generation technologies. Various Use Cases are detailed, highlighting the pivotal roles that Non-Terrestrial Networks play in distinguishing between urban/suburban and rural environments, with particular emphasis on transportation ecosystems. Through this analysis, Key Performance Indicators and requirements are delineated to characterize the requisite service quality for these diverse Use Cases. The paper further presents an overview of potential and standards-compliant integrated Terrestrial/Non-Terrestrial architectures, delineating their roles both in backhauling and access across different layers of Non-Terrestrial systems and elements. These insights are derived from studies conducted within the Integrated Terrestrial And Non-Terrestrial Networks (ITA-NTN) project, part of the European Union initiative defined as the Italian National Recovery and Resilience Plan (NRRP) RESTART Research Program.

Multi-access Edge Computing represents a key enabling technology for emerging mobile networks. It offers intensive computational resources very close to the end-users, useful for task offloading purposes. Many scientific contributions already proposed approaches for optimally allocating these resources over time. However, most of them fail to take advantage of the prediction of both users’ mobility and service demands over a look-ahead temporal horizon. To bridge this gap, this paper formulates a novel methodology for anticipatorily allocating communication and computational resources at the network edge, based on the prediction of spatio-temporal dynamics of mobile users. The conceived architecture exploits a Software-Defined Networking approach to monitor users’ mobility, a Convolutional Long Short-Term Memory to predict over different look-ahead horizons the number of users within a given number of cells and their related service demands, and Dynamic Programming to optimally allocate users’ requests among available Multi-access Edge Computing servers. Computer simulations investigate the effectiveness of the proposed approach in a realistic autonomous driving use case and compare its behavior against a baseline solution. Obtained results demonstrate its unique ability to dynamically and fairly distribute users’ requests among the resources available at the network edge, while ensuring the targeted quality of service level.