HORIZON EUROPE, SNS-JU: AI-Enhanced fibre-Wireless Optical 6G network in support of Connected mobility (6G-EWOC)

Jan. 2024 - Dec 2026. Call: PILAR II: GLOBAL CHALLENGES & EUROPEAN INDUSTRIAL COMPETITIVENESS IP: José Antonio Lázaro (UPC)

The sixth generation (6G) of wireless communication technology is heralded as an enabler of our digital age. It offers vast potential for individuals and businesses to enhance opportunities and create new technologies across a broad range of sectors, including industrial manufacturing, energy supply, digital healthcare, government and education, and efficient transportation. 6G-EWOC: AI-Enhanced Fibre-Wireless Optical 6G Network in Support of Connected Mobility, contributes to this mission with a focus on autonomous driving. By connecting vehicles and instantaneously making their collected information available to all traffic participants, 6G provides a key safety and efficient transportation feature. 6G-EWOC brings critical technologies to the forefront:

• Optical wireless communications and sensing for situational awareness and connectivity.
• Seamless access to edge data centres through a high-capacity fibre fronthaul.
• Real-time processing of collected roadside data.
• Orchestration of various elements of 6G-enabled vehicular connectivity through artificial intelligence.

HORIZON-SNS SElf-mAnaged Sustainable high-capacity Optical Networks (SEASON)

Jan. 2023 - Jan. 2026. Call: HORIZON-JU-SNS-2022. IP: Luis Velasco Esteban (coordinated from CNIT - National Inter-University Consortium for Telecommunications)

The goal of the SEASON project is to design and validate a sustainable transport network infrastructure able to support beyond 5G and new emerging services. The SEASON infrastructure will rely on the joint usage of Multi-Band (MB) and Space Division Multiplexing (SDM), spanning the access, aggregation, and metro/long-haul segments, supporting the requirements for x-haul, further integrating the packet/optical and computing layers, and targeting cost-effective capacity increase. A critical objective of such architecture is to ensure energy efficiency. SEASON will rely on power-efficient Digital Signal Processing (DSP), MBoverSDM optical switching, point-to-multipoint transceivers allowing traffic aggregation/router bypassing, and converged packet-optical solutions reducing the number of O/E/O conversions. Such complex infrastructure requires rethinking the control and orchestration systems towards autonomous optical networks, addressing not only the integration - in overarching control systems - of the Radio Access Network (RAN), access and transport segments but also adopting more agile DevOps methodologies. SEASON will leverage on cognitive networks powered by streaming telemetry, real-time network measurements and Artificial Intelligence/Machine Learning (AI/ML)-aided service management and orchestration for near-real time network operation, moving intelligence as close as possible to the data plane, and devising a distributed system based on multiple communicating agents and data-driven closed control loops. SEASON will have a clear impact on the society, in a context with increased needs of connectivity and higher capacity demand required for services such as VR/AR. The SEASON consortium includes major European telecom operators (Telefonica, TIM), major vendors (ADVA, Infinera P/G, Ericsson), three consolidated SMEs (Accelleran, Wings and WestAquila) and four top-reputed research centres and academia (CNIT, CTTC, Fraunhofer HHI, and UPC).

HORIZON-SNS Deep Programmability and Secure Distributed Intelligence for Real-Time End-to-End 6G Networks (DESIRE6G)

Jan. 2023 - Dec. 2025. Call: HORIZON-JU-SNS-2022. IP: Luis Velasco Esteban (coordinated from University of Amsterdam)

Over the past decades the mobile communications has evolved over the different generations to the current 5G, and transformed into a fundamental infrastructure that supports digital demands from all industry sectors. However, 5G systems are expected to fall short on meeting the anticipated stringent performance requirements for the new generation of real time mission-critical applications. In view of that, DESIRE6G will design and develop novel zero-touch control, management, and orchestration platform, with native integration of AI, to support eXtreme URLLC application requirements. DESIRE6G will re-
architect mobile networks through a) its intent-based control and end-to-end orchestration that targets to achieve near real time autonomic networking; and b) a cloud-native unified programmable data plane layer supporting multi-tenancy. The latter will be supported by a generic hardware abstraction layer designed for heterogeneous systems. Flexible composition of modular micro-services for slice specific implementations and flexible function placement depending on HW requirements will enable granular use case instantiation and service level assurance with minimum resource consumption and maximum energy efficiency. The DESIRE6G data, control, management, and orchestration plane is supported by a pervasive monitoring system, extending from the network to the user equipment or IoT terminal. DESIRE6G will employ distributed ledger technology to support a) dynamic federation for services across of multiple administrative domains and b) infrastructure-agnostic software security. Finally, DESIRE6G will enable communication-, and energy- efficient distributed AI, at the network edge, while considering application-level requirements and resource constraints. The proposed innovations will be validated employing a VR/AR/MR and a Digital Twin application at two distinct experimental sites.

HORIZON-SNS PRogrammable AI-Enabled DeterminIstiC neTworking for 6G (PREDICT-6G)

Jan. 2023 - July 2025. Call: HORIZON-JU-SNS-2022. IP: Luis Velasco Esteban (coordinated from UC3M)

6G is envisioned to accelerate the path started in 5G for catering to the needs of a wide variety of vertical use cases, both current and emerging. This will require major enhancements of the current 5G capabilities especially in terms of bandwidth, latency, reliability, security, and energy. PREDICT-6G's mission is therefore set towards the development of an end-to-end 6G (e2e) solution including architecture and protocols that can guarantee seamless provisioning of services for vertical use cases requiring extremely tight timing and reliability constraints. To succeed, the solution will target determinism network infrastructures at large, including wired and wireless segments and their interconnections. PREDICT-6G will develop a novel Multi-technology Multi-domain Data-Plane (MDP) overhauling the reliability and time sensitiveness design features existing in current wired and wireless standards. The ambition is for the MDP design to be inherently deterministic. To achieve this, PREDICT-6G will develop an AI-driven Multi-stakeholder Inter-domain Control-Plane (AICP) for the provisioning of deterministic network paths to support time sensitive services as requested by end-customers and with different scaling ambitions, e.g., from the network in a single vehicle to a large, geographically dispersed network. This requires timely monitoring and prediction of the behavior of the complete network, including identifying potential sources of quality violations and analyzing various routes of the traffic flows. These capabilities will be delivered through the PREDICT-6G AI-powered Digital Twin (DT) framework, allowing the prediction of the behavior of the end-to-end network infrastructure, and enabling anticipative control and validation of the network provisions to meet the real-world time-sensitive and reliability requirements of the running services.

UNICO5G Towards a smart and effIcient telecoM Infrastructure meetiNG current and future industry needs (TIMING)

Jan. 2022 - Dec. 2024. Call: UNICO-5G I+D. IP: Luis Velasco Esteban

Identifying Industry 4.0 as a key vertical, TIMING targets to design a solution to enable e2e reliable TSN services supported by operators' infrastructures that are currently carrying on a best effort basis. TIMING will analyze TSN support in the Ethernet and Wi-Fi segments and identify the enhancements to be made for supporting the sub-millisecond latency for TSN systems. Scheduling solutions to support these enhancements will be devised. In addition, solutions to automate the deployment of e2e TSN services with assured performance will be designed. Such service automation relies on a control plane, which will include a TSN controller able to control and monitor Ethernet and Wi-Fi TSN nodes, a TSN Connectivity Manager to provide e2e connectivity across TSN and non-TSN segments, and a QoS estimation tool that includes accurate TSN traffic models. TIMING will build PoC demonstrators validating the whole TIMING architecture. The POC will demonstrate: (1) at the modeling level, a tool that evaluates the performance of the new TSN service to be deployed and the impact on the existing services (TSN and/or BE traffic); (2) at the control plane, the capability to deploy reliable e2e TSN services with committed performance in terms of e2e delay; and (3) at the infrastructure level, the capability to transport TSN traffic between two TSN domains: one with Automated Guided Vehicles (AGVs) emulating a factory, and the other with the AGV's controller, which requires bounded latency communications with the AVs; other services for loading the system will be also included. Finally, TIMING will maximize impact by influencing major vendors and service providers on the adoption of the developed principles through communication, dissemination, and standardization activities, while exploiting the results and knowledge obtained, and contributing to the digital transition of the industry and the green deal.

MENTOR: Machine LEarning in Optical NeTwORks

Jan. 2021 - Dec. 2024. Call: H2020-MSCA-ITN-2020. IP(at UPC): Luis Velasco Esteban (coordinated from Aston Univ.)

Optical fiber networks is one of the major drivers of our societal progress and a key enabler of the global telecommunication infrastructure. Optical networks underwent considerable changes over the past decade, as consequence of a continuous growth (exceeding 20% per year) of bandwidth demand. The current growth sets strong requirements in terms of capacity and costs for the operators, which seek to decrease the cost per transmitted bit. Several solutions have been proposed, and among them wide-band is more favorable to network operators. However, wide-band optical system presents new major challenges: optical components must guarantee similar performance over a broad spectrum, network optimization is carried out on a non-flat spectrum and with a much larger number of channels making design, optimization and control a complex problem. Therefore, application of machine learning (ML) techniques is of the growing importance for high-capacity multi-band (MB) optical systems. ML is becoming the technique of choice to solve complex nonlinear technical problems, such as, advance component design and management of wide-band networks. The European Industrial Doctorate MENTOR presents a timely proposal to train 6 ESRs in the interdisciplinary field of high industrial importance: ML applications in multi-band optical communications. As ML can properly work only when a large amount of real data is available, it is crucial to bring together academic partners and the industry that provide access to the data.

B5G-OPEN: Beyond 5G – OPtical nEtwork coNtinuum

Nov. 2021 - Oct. 2024. Call: H2020-ICT-2020-2. IP(at UPC): Luis Velasco Esteban (coordinated from Telefonica)

B5G-OPEN targets the design, prototyping and demonstration of a novel end-to-end integrated packet-optical transport architecture based on MultiBand (MB) optical transmission and switching networks. MB expands the available capacity of optical fibres by enabling transmission within S, E, and O bands, in addition to commercial C and/or C+L bands, which translates into a potential 10x capacity increase and low-latency for services beyond 5G. To realize multiband networks, technology advances are required, both in data, control and management planes. Such technology advances complement novel packet-optical white boxes using flexible sliceable Bandwidth Variable Transceivers and novel pluggable optics. The availability of MB transmission will also lead to a complete redesign of the end-to-end architecture, removing boundaries between network domains and reducing electronic intermediate terminations.

The control plane will be extended to support multiband elements and a 'domain-less' network architecture. It will rely on physical layer abstraction, new impairment modelling, and pervasive telemetry data collection to feed AI/ML algorithms that will lead to a Zero-Touch networking paradigm including a full featured node operating system for packet-optical whiteboxes.

The results will be shown in two final demonstrations exposing the project benefits from operator and user perspectives. B5G-OPEN will have a clear impact on the society showing the evolution towards a world with increased needs of connectivity and higher capacity in support of new B5G services and new traffic patterns.

TRAINER: TowaRds fully AI-empowered NEtwoRks

Sept. 2021 - Aug. 2024. Call: Proyectos I+D+i 2020. IP: Salvatore Spadaro

The upcoming 6G services will dramatically increase requirements on many network Key Performance Indicators versus 5G, such as peak data rates, latencies and with ultra-high reliability. Actually, 5G and beyond networks (6G) have to support a combination of several types of workloads stemming from a variety of use cases/verticals.These workloads can come and go and may even change dynamically during services lifetime. As a result, the derived requirement from the networks may change often and these changes may be significant. Therefore, the networks must constantly adapt to and anticipate changes, increasing thus dramatically the network complexity. The observation that certain trends in network behavior can be predicted and actions taken in anticipation, leads to the introduction of AI/ML. Actually there is huge potential for Artificial Intelligence (AI) to improve management and performance of Beyond 5G networks which are expected to be developed in the years to come. Indeed, AI/ML technologies offer the potential to efficiently address the challenges of complex 5G and beyond networks. In particular, the TRAINER project will encompass different network segments (optical Metro/Access, Mobile Edge Computing (MEC) servers/central data centers). The ambitious innovation that TRAINER will bring reside on the concept of having AI/ML distributed at all levels of the SDN/NFV technology domain, including AI/ML-enabled end-to-end service orchestration, cognitive network management and even at optical data plane for quality of transmission assurance and signal processing.

IBON: AI-powered Intent-Based packet and Optical transport Networks and edge and cloud computing for beyond 5G

Sept. 2021 - Aug. 2024. Call: Proyectos I+D+i 2020. IP: Luis Velasco Esteban

IBON will design and build a ubiquitous, secure and explainable Artificial Intelligence (AI)-powered intent-based networking (IBN) platform that spans end-to-end (from terminals to the RAN and transport network and from edge to cloud computing) and is aware of its state and context to autonomously take proactive actions for service assurance.

The IBN platform is integrated in a zero-touch control and orchestration platform featuring an AI Function Orchestrator to manage AI pipelines. The objective is to create an AI-assisted elastic and dynamic infrastructure supporting per-domain and e2e networks and services real time (RT) e2e operation automation, ensuring near-RT decision making and non-RT tight coordination. Specific components will be developed and integrated to create an agile platform that goes well beyond 5G and supports application-level resilience and intelligence through replication and elasticity. Demonstration will be carried out in an experimental environment.

The project will actively contribute to relevant standardization bodies and open source projects to promote IBON solutions to the wider community. IBON has the potential to create a significant shift in the way telecom services are commercialized, representing new market/higher volume opportunities for vendors, and tremendous potential for start-ups creating specialized applications.

ARTIST: Smart Radio Access Integration of User Devices

Sept. 2021 - Aug. 2024. Call: Proyectos I+D+i 2020. IP: Oriol Sallent Roig

The vision of the smART radIo acceSs with inTegration of user devices (ARTIST) project is a Beyond 5G (B5G) scenario where the User Equipment (UE) is exploited not only to satisfy the specific needs of the UE owner but also to augment the Radio Access Network (RAN) infrastructure as a distributed capability and as a source of network intelligence. In other words, we envision the idea of UEs taking a more active role in network service provisioning as one of the key pillars to ground future mobile network evolution, to the extent that the very notion of a cell will have to be rethought as UEs will be able to actively complement the RAN infrastructure. This constitutes a radical paradigm shift from UEs operating only as Network Service Consumers towards embracing UEs also as Network Service Providers. That is, utilizing UEs as an extended computing, storage and networking element of the B5G RAN infrastructure as well as a central element for the realization of end-to-end connected network intelligence.

The ARTIST concept with its intrinsic connected intelligence will contribute to solving and/or mitigating a wide range of problematics that are inherent to wireless networks. Remarkably, the realization of ARTIST paves the way for enhanced service quality (e.g., enhanced coverage, better mobility management, user behavior and demand prediction), higher radio resource utilization efficiency (e.g., more efficient radio resource allocation, congestion control, better beam management), improved system performance (e.g., on device inference reduces network data traffic for more efficient mobility and spectrum utilization, better link adaptation can be attained through position[1]aware interference prediction) and simplified RAN deployment and operation (e.g., more capable Self Organizing Networks for e.g., mmWave network densification, reduced energy consumption).