Abstract: 5G-DIVE targets end-to-end 5G trials aimed at proving the technical merits and business value proposition of 5G technologies in two vertical pilots, namely (i) Industry 4.0 and (ii) Autonomous Drone Scout. These trials will put in action a bespoke end-to-end 5G design tailored to the requirements of the applications targeted in each vertical pilot, such as digital twinning and drone fleet navigation applications. 5G-DIVE’s bespoke design is built around two main pillars, namely (1) end-to-end 5G connectivity including 5G New Radio, Crosshaul transport and 5G Core, and (2) distributed edge and fog computing integrating intelligence located closely to the user. The latter pillar extends significantly beyond the EU- TW-Phase-I 5G-CORAL solution framework by adding support for automation based on artificial intelligence and distributed ledger technologies. The targeted intelligent tailored design is envisioned to achieve optimized performance and thus boost significantly the business value proposition of 5G in each targeted vertical application. 5G-DIVE trials target pilots running for several weeks on the premises of the vertical applications in real-life testbeds in Europe and Taiwan, leveraging noticeably the European 5G end- to-end facilities from ICT-17 call and Taiwan’s testbed facilities.

Europe has a lack of intellectual property in integrating artificial intelligence (AI) into digital applications. This is critical since the automatization reached saturated levels and AI in digitisation is an accepted approach for the upcoming transformation of the European industry. The potential of AI in economy and society is by far not enough exploited. Potential users of AI are not sufficiently supported to facilitate the integration of AI into their applications. Enabling of performance, industry and humanity by AI for digitising industry is the key to push the AI revolution in Europe and step into the digital age. Existing services providing state of the art machine learning (ML) and artificial intelligence solutions are currently available in the cloud. In this project, we aim to transfer machine learning and AI from the cloud to the edge in manufacturing, mobility and robotics. To achieve these targets we connect factories, processes, and devices within digitised industry by utilizing ML and AI for human machine collaboration, change detection, and detection of abnormalities. Hence, we gain knowledge by using existing data and arrange them into a processable representation or collect new data. We use this knowledge to change the semantics and the logical layer with a distributed system intelligence for e.g. quality control, production optimization. In AI4DI, we define a 7-key-target-approach to evaluate the relevance of AI methods within digitised industry. Each key target represents a field of activity and the corresponding target at the same time, dividing systems into heterogenous and homogenous systems, and evolving a common AI method understanding for these systems as well as for human machine collaboration. Furthermore, we investigate, develop and apply AI tools for change detection and distributed system intelligence, and develop hardware and software modules as internet of things (IoT) devices for sensing, actuating, and connectivity processing.

Key objectives of METIS-II are to develop the overall 5G radio access network design and to provide the technical enablers needed for an efficient integration and use of the various 5G technologies and components currently developed. The innovation pillars that will allow METIS-II to achieve this goal are • a holistic spectrum management architecture addressing the spectrum crunch, • an air interface harmonisation framework enabling an efficient integration of new and legacy air interfaces, • an agile Resource Management (RM) framework providing the dynamics required to efficiently adapt the integrated 5G air interfaces and radio concepts to the varying traffic demand and service requirements, • a cross-layer and cross-air-interface system access and mobility framework ensuring an ubiquitous access continuum, • and a common control and user plane framework providing the means for an efficient support of the broad versatility of services expected for 5G as well as a future-proof and cost-efficient implementation of the 5G integration. On the strategic level, METIS-II will provide the 5G collaboration framework within 5G-PPP for a common evaluation of 5G radio access network concepts and prepare concerted action towards regulatory and standardisation bodies. Based on its very strong and international consortium with partners from all regions with strong 5G R&D initiatives (EU, US, China, Japan, Korea) with most of the major international vendors, major operators, and key researchers, METIS-II will have the unique capability to drive consensus building globally, to consolidate a full picture of the needs of mobile as well as vertical industries, and to disseminate the results towards the relevant bodies, forums, and standardisation groups in all regions. The METIS-II proposal addresses the Strand “Radio network architecture and technologies” in the ICT14-2014 call in the H2020 program. METIS-II is committed to actively drive the collaboration with the 5G-PPP.

Mobile data traffic is forecasted to increase 11-fold between 2013 and 2018. 5G networks serving this mobile data tsunami will require fronthaul and backhaul solutions between the RAN and the packet core capable of dealing with this increased traffic load while fulfilling new stringent 5G service requirements in a cost-efficient manner. The 5G-Crosshaul project aims at developing a 5G integrated backhaul and fronthaul transport network enabling a flexible and software-defined reconfiguration of all networking elements in a multi-tenant and service-oriented unified management environment. The 5G-Crosshaul transport network envisioned will consist of high-capacity switches and heterogeneous transmission links (e.g., fibre or wireless optics, high-capacity copper, mmWave) interconnecting Remote Radio Heads, 5GPoAs (e.g., macro and small cells), cloud-processing units (mini data centres), and points-of-presence of the core networks of one or multiple service providers. This transport network will flexibly interconnect distributed 5G radio access and core network functions, hosted on in-network cloud nodes, through the implementation of: (i) a control infrastructure using a unified, abstract network model for control plane integration (5G-Crosshaul Control Infrastructure, XCI); (ii) a unified data plane encompassing innovative high-capacity transmission technologies and novel deterministic-latency switch architectures (5G-Crosshaul Packet Forwarding Element, XFE). Demonstration and validation of the 5G-Crosshaul technology components developed will be integrated into a software-defined flexible and reconfigurable 5G Test-bed in Berlin. Mobility-related 5G-Crosshaul experiments will be performed using Taiwan’s high-speed trains. 5G-Crosshaul KPI targets evaluated will include among others a 20% network capacity increase, latencies <1 ms and 30% TCO reduction. The 5G-Crosshaul proposal addresses the ICT 14-2014 call of the Horizon 2020 Work Programme 2014-15 with a special focus on the P7 objectives defined by the 5GPPP IA