One of the key enablers of 6G is undoubtedly the Native support of AI/ML at all the system levels, components, and mechanisms, from the orchestration and management levels to the low-level optimization of the infrastructure resources, including Cloud, Edge, RAN, Core Network, as well as a transport network. Despite the opportunities, there are several gaps that hinder the adoption of AI/ML in 6G, such as the lack of extensive and high-quality datasets that are required to train the models. On the other hand, AI model testing and performance evaluation in a representative staging environment (by emulation or real deployment) is also challenging without access to an end-to-end 6G testbed or representative Digital Twin environment. To this end, 6G-DALI aims to deliver an end-to-end AI framework for 6G, structured in two interdependent pillars, (1) AI experimentation as a service via MLOps and (2) Data and analytics collection and storage via DataOps. The 6G-DALI DataOps pillar provides the mechanisms for preparing clean and processed data that are stored within a 6G Dataspace and are made available for training and validating machine learning models as a service, a part of the MLOps Pillar. The end-to-end framework also delivers continuous monitoring, drift detection and retraining of models. Finally, 6G-DALI will deliver open datasets, a 6G Dataspace for dataset storage and secure sharing, and a Digital Twin testbed for data generation on demand.

The expected obsolescence of GSM-R and the need to enable digitalisation in train operations has led the European railway sector to set a global plan for the definition of a new radio system, the Future Railway Mobile Communication System (FRMCS), as presented in the EU-Rail System Pillar Report on FRMCS V2 and V3 Scope and Planning (ref. SPG-STG-D-SPG-076-01). A key part of this plan is the delivery by UIC, in the frame of its FRMCS Program, of the FRMCS V3 specifications, also named “FRMCS 1st Edition”, corresponding to the first implementable version of the new system, for their inclusion in a new CCS-TSI in 2027. Starting from the final UIC FRMCS V2 Specifications & V3 target requirements, expected by December 2024 as a result of the ERA EECT process, there will be consequently a need to verify, complete or amend these V2 Specifications & V3 target requirements through a full testing of FRMCS functions and system, leading then to market ready V3 Specifications. This operational testing is precisely the objective of FP2-MORANE-2 (MObile radio for RAilway Networks in Europe). The first step of the testing activities will be achieved in 3 different labs, run by Ericsson, Nokia and Kontron. They will be followed by 5 different field tests, operated on two railway tracks from ADIF, one from DB, one from TRAFIKVERKET and one from PRORAIL. 4 of these lines are conventional, the 5th, in ADIF network, being a high-speed line. The PRORAIL line will welcome a MNO, KPN. The FP2-MORANE-2 project, coordinated by UIC, takes advantage of the participation of 13 European railways, from which 7 will act as associated partners. It regroups the expertise of 13 product manufacturers, all recognised as key players in the FRMCS domain, and finally benefits from the contribution of UNIFE. Conceived as a continuation of all previous FRMCS activities, such as Horizon 2020 5GRAIL prototyping project or EU-Rail R2DATO FRMCS-related work packages, FP2-MORANE-2 will set the way for FRMCS deployments in Europe, as its predecessor MORANE did for GSM-R 20 years ago.

Context-awareness is essential for many existing and emerging applications. Context information greatly relies on location information of people and things. But, navigation satellite systems are denied in indoor environments, current cellular systems fail to provide high-accuracy localization, other local localization technologies (e.g. WI-FI or BT) imply high deployment/maintenance/integration costs. Raw spatiotemporal data are not sufficient by themselves and need to be integrated with tools for the analysis of the behaviour of physical targets, to extract relevant feature of interests. LOCUS will improve the functionality of 5G infrastructures to: i) provide accurate and ubiquitous location information as a network-native service and ii) derive more complex features and behavioural patterns out of raw location and physical events, and expose them to applications via simple interfaces. Localization, together with analytics, and their combined provision “as a service”, will greatly increase the overall value of the 5G ecosystem, allowing network operators to better manage their networks and to dramatically expand the range of offered applications and services. The current freedom to act on 5G system design and availability of software network paradigms and AI techniques uniquely combine in this historical moment to make it possible to radically improve the future network by endowing it with accurate on-demand localization and analytics. LOCUS will showcase its solutions in three scenarios: Smart Network Management based on Location Information of 5G equipment; Network-assisted Self-driving Objects; People Mobility & Flow Monitoring. The LOCUS consortium gathers a diverse blend of high-profile partners including Operators, Vendors, IT industries and SMEs that can make its vision a reality. LOCUS will be an enabler of a myriad of applications for the 5G ecosystem and beyond, boosting vertical industries and creating new business opportunities also for telcos.