ARCFIRE will bring RINA from labs into the real-world. RINA, the Recursive InterNetwork Architecture, is an innovative “back-to-basics” network architecture that solves current limitations and facilitates full integration between distributed computing and networking. RINA addresses the challenges that drive the communications industry in moving from dedicated hardware to almost completely virtualised infrastructure. The next shift, 5G, on the horizon for 2020, will change the communication industry even more significantly. Now is the right time for ARCFIRE to provide experimental evidence of RINA’s benefits, at large scale, in compelling and realistic business cases, thus motivating RINA adoption. ARCFIRE will experimentally demonstrate RINA’s key benefits integrating current EC investment in advanced networks (IRATI, PRISTINE) and Future Internet testbeds (FIRE+) focusing on 5 goals: 1) Facilitate comparison of converged operator networks using RINA to operator’s current network designs; 2) Produce a robust RINA software suite ready for Europe to engage in large-scale deployments and long-living experiments; 3) Provide relevant experimental evidence of RINA benefits to network operators, their equipment vendors, application developers and end-users; 4) Build on the current EU Future Internet community and raise the number of organisations involved in RINA development and deployment; 5) Enhance the FIRE+ infrastructure with ready to use RINA software. ARCFIRE will have long-term sustainable impact on how we build infrastructure for the Networked Society. ARCFIRE’s deployed software suite will enable equipment vendors to shorten their innovation life cycle, network operators to run advanced networks addressing their needs in a future-proof fashion, European SME’s to find and exploit specialised markets and application developers to explore unseen opportunities. ARCFIRE’s consortium has the experience and resources to achieve these goals and provide this impact.

BeGREEN will take a holistic view to propose evolving radio networks that not only accommodate increasing traffic and services but also consider power consumption as a factor. Determining the metrics by which power consumption should be included is a key feature which will be studied as first stage of the project. This will include not only the cost of the energy but also societal factors. BeGREEN will evaluate different mechanisms by which power consumption could be reduced based on the following pillars: At the architecture level, planning and evaluation of a massive MIMO included RAN design to achieve flexible and energy efficient connectivity considering spectrum utilisation, interference mitigation and architecture/processing complexity. At the hardware and infrastructure level, radio-unit controlling schemes will be used in power amplifiers energy optimisation. Also, an offloading engine for hardware acceleration will be employed to achieve energy efficiency when performing radio access functions and network function virtualisation. At the link level, the integrated sensing techniques are used to provide a better estimate of the impact of the radio channel toward improvements in spectral efficiency against the increased power consumption associated with the resulting calculations. At the system level, the project pursues the development and evaluation of AI-based procedures to adapt the energy consumption of softwarised network functions, aiming to minimize the overall consumed energy according to the utilisation patterns of network. BeGREEN proposes an “Intelligent Plane”, as an additional plane along with user plane and data plane, that allows the data, model and inference to be seamlessly exchanged between network functions. BeGREEN will use O-RAN as the baseline architecture, due to new/suitable interfaces and protocols it can provide, to be used for the movement of data around the network to the appropriate location for performance and efficiency assessments. In addition, the disaggregation, virtualisation and network and service management capabilities inherent in O-RAN provide the mechanisms to realise many of the infrastructure changes and techniques for energy optimisation pursued in BeGREEN. BeGREEN will use AI/ML techniques to provide solutions for reducing the required calculations and to recognise patterns in the system level data associated with the behaviour of the user-base and to learn the most appropriate response to this behaviour in terms of both network performance and energy consumption. In this scheme, impact of the location of the AI/ML operations within the network on the performance of the approach, the consumption of power and the ability to share resources between different operations will be considered. BeGREEN technologies will be showcased in three demonstrations. At IHP premises, the joint communications and sensing techniques toward efficient resource allocation and optimised power consumption. The project targets using reconfigurable intelligent surfaces for energy saving scenarios in the demonstrations. Furthermore, two major project demonstrations will be performed at BT premises in Adastral park. First, the ‘Intelligent Plane’ implemented using ORAN rApps and xApps will be demonstrated on a network emulator. Then, the project final integrated demonstrator using the Adastral testbed facilities to showcase BeGREEN technology innovations.

GENerative and connected intelligence for 6G Open ManagemEnt (GENOME) research and training programme aims at investigating, developing/fine-tuning and validating large language models (LLMs) for the autonomous management and orchestration of various network technological domains (O-RAN, edge, cloud) through intent-based networking and task-agnostic network functions. It also targets the establishment of a connected intelligence framework for the coordination between these functions via on-the-fly protocol learning to mitigate conflicting management decisions and maximize utilization. Network configuration will also be generated automatically through innovative neuro-symbolic AI algorithms. Moreover, the transparency and resilience of the AI models is researched. All the developed components will be validated via both simulation and testbed experiments, and integrated into a final proof-of-concept. Besides, a detailed training plan is designed including schools, industrial days and soft-skills courses. It involves industrial partners to ensure that career perspectives of ESRs will be significantly increased by participation in the project. High quality dissemination and exploitation activities are also considered.

The 6G Smart Networks of the future will provide the high-performance and energy-efficient infrastructure on which next generation internet and other services can be developed and deployed. 6G will foster an Industry revolution and digital transformation and will accelerate the building of smart societies leading to quality-of-life improvements, facilitating autonomous systems, haptic communication and smart healthcare. To achieve the aforementioned objectives in a sustainable way, it is well understood that new approaches are needed in the way the telco infrastructures are architected, federated and orchestrated. These new approaches call for multi-stakeholder ecosystems that promote synergies among MNOs and owners of all kinds or computational and networking resources that will share the extraordinary costs of yet another generation upgrade from 5G to 6G, while facilitating new business models. It is clear, that the new architecture paradigms bring unprecedented complexity due to the sheer scale and heterogeneity of the orchestration domains involved, that should be matched by equally capable automation capabilities, thus 6G is aiming for the “holy grail” of pervasive AI-driven intelligence, termed as Native AI. However, the multi-stakeholder infrastructures foreseen in 6G as per the “network of networks” concept, will add a level of unprecedented management complexity due to the sheer scale and heterogeneity of the orchestration domains involved. 6G-INTENSE aims to abstract and federate all kinds of computational and communication resources under an internet-scale framework, that is governed by an intelligent orchestration paradigm, termed as DIMO.