PREDICT-6G

Deterministic services for critical communications

By Péter Szilágyi, Technical Manager

A communication may be considered critical if the functional capability, operational capacity, and safety of the communication endpoints and their implemented solution depend on the communication service’s availability, reliability, and performance. In such scenarios, the communication and thus the underlying network play an inseparable role in realizing an end-to-end solution. Example scenarios include cloud robotics; factory automation (e.g., implementing manufacturing or production workflows); AR/VR based interactions (potentially extended with cloud annotations); distributed sensor data collection, analytics, and command & control of physical devices; and many others. In such cases, the operation of the end devices, cloud application and the overall end-to-end solution imposes deterministic requirements on the network and communication service that interconnects them. 

Mobile devices such as AGVs, drones, AR/VR headsets or even smartphone-based applications may also engage in collaborative tasks executed in the physical space requiring deterministic service. It requires that the network can provide deterministic communication within a dynamically evolving group, where devices are joining/leaving a group in an ad-hoc manner according to, e.g., the interest of their users, their interaction in the virtual space, their mobility or physical proximity. 

Cloud applications may be responsible for the monitoring and control of the devices and serving as rendezvous points to enable cloud-based group communication and data sharing across a large set of distributed devices that share a common task, physical or virtual environment or mission. In all these cases, it is important that the devices and the cloud applications participating in the same collaborative relation stay synchronized concerning their shared application state and thus need to exchange information, data, commands, and contextual information through deterministic and reliable communication services.

The Nokia Open Lab will implement and demonstrate use cases related to the critical communication requirements, which may manifest in concrete scenarios such as real-time sensor data collection and machine control; group communication of multiple devices via a rendezvous point; or camera sharing across multiple devices.

If you want to stay updated about PREDICT-6G, subscribe to our newsletter and follow us on Twitter and LinkedIn!

by PREDICT-6G

DEMO: Target Wake Time (POLITO)

Use cases are at the heart of PREDICT-6G. They are the way for our research and use case providers to experiment, validate and demonstrate how PREDICT-6G technologies enable a reliable, predictable and time-engineered 6G network. Claudio Casetti, Full Professor at Politecnico di Torino and a researcher in the PREDICT-6G consortium led the “Target Wake Time” demo.

This demonstration shows the evolution of Wi-Fi networks with the introduction of Target Wake Time (TWT), a feature that transforms the way devices communicate within a network. Traditionally, Wi-Fi networks were based on CSMACA principles, which allowed efficient collision resolution but introduced randomness in channel access and transmission timing. The demonstration delves into how TWT, initially introduced in 802.11 AH and later integrated into Wi-Fi 6 (802.11 AX), addresses these challenges. 

Using simulations with 8 strategically spaced stations, the demonstration compares TWT-enabled communication with standard Wi-Fi, highlighting TWT's deterministic latency and significant energy savings.

You can watch the demo here and below.

If you want to stay updated about PREDICT-6G, subscribe to our newsletter and follow us on Twitter and LinkedIn!

by PREDICT-6G

DEMO: Smart Factory (Gestamp and Ericsson)

Use cases are at the heart of PREDICT-6G. They are the way for our research and use case providers to experiment, validate and demonstrate how PREDICT-6G technologies enable a reliable, predictable and time-engineered 6G network. Marc Mollà, Chief Solution Architect at Ericsson and a member of PREDICT-6G, led the "Smart Factory" demo.

This demonstration shows the application of Time Sensitive Networking (TSN) capabilities in 3GPP networks, with a specific focus on a Gestamp -inspired smart factory use case. The objective is to move from a wired configuration to a wireless LAN scenario using a 5G network, emphasising the challenges of interconnecting numerous mobile components in a factory environment.

Overall, the demo highlights the potential integration of TSN enhancements into 5G systems, offering improved spectrum sharing, reduced network congestion, and enhanced reliability for mission-critical industrial applications, even without specialised TSN-supported hardware like commercial UE's or Ethernet-based protocols.

You can watch the demo here and below.

If you want to stay updated about PREDICT-6G, subscribe to our newsletter and follow us on Twitter and LinkedIn!

by PREDICT-6G

One year of PREDICT-6G: 2023 review

By Antonio de la Oliva, Project Coordinator

The end of 2023 marks also the closing of the first year of the PREDICT-6G project. During this year, several key milestones have been achieved, setting the basis for the technical work of the second year. During the first months of 2023, PREDICT-6G focused on understanding the use cases which may benefit from deterministic networking innovations. The three use cases defined in the proposal - Smart manufacturing, Deterministic services for critical communications and multi-domain deterministic communications - have been extended to Localisation and Sensing, XR and IETF RAW and DetNet. With the inclusion of these new use cases, we believe the project sufficiently covers the requirements of current industries.

Based on the requirements and expected KPIs of the identified use cases, the main efforts of the year 2023 were dedicated to developing the system architecture and the principles of the Multi-Domain Dataplane (MDP) in WP2 and the AI-driven multi-stakeholder inter-domain Control Plane (AICP) in WP3. The work on the MDP and AICP design was synthetised into a full architecture specification, including E2E and domain level management service definition, E2E deterministic service architecture and lifecycle, MDP architecture and cross-domain U-plane integration enablers, system and service procedures, and Open APIs for technology integration with 3GPP and IETF DetNet domains.

Regarding the MDP, innovation areas were explored in the data-plane to enable cross-domain deterministic services, such as deterministic service continuity at domain borders, deterministic scheduler designs, cross-domain split of reliability and deterministic enablers, and time sync across multiple domains. Technologies consider 3GPP (with and without IETF DetNet integration support), IEEE TSC (with IETF DetNet), and novel Wi-Fi MAC capabilities. To support these technologies at the control level, the project follows an OpenAPI methodology defining the programmability layer on top of a network segment with the selected deterministic technologies, or even over network domains with no explicit support for determinism. The OpenAPIs are the interface between the PREDICT-6G MDP and AICP, enabling the technology-agnostic design for the AICP architecture. Current discussion within the project is the relation of the OpenAPIs with the DetNet component, and whether all different domains should be integrated below the DetNet control.

At its own pace, the AICP has also evolved significantly during 2023. The AICP follows a service-based architecture principle, where Management Services (MS) interact with each other via clearly defined APIs. MSs that share the same management scope are organised into Management Domains (MD). AICP defined a single MD for the E2E deterministic services, as well as separate MDs for each of the technology domains that are part of the initial release of PREDICT-6G’s MDP. This role split enables the AICP to govern any number of technological domains (i.e., 3GPP, IETF DetNet / IEEE TSN, Wi-Fi, and more) driven by the same end-to-end service focus. Individual Management Services implement capabilities such as service ingestion, service automation, path computation, digital twinning, AI-based predictions, measurement collection, and the exposure of topology, services, resources, and capabilities from domain level to end-to-end and from end-to-end to the consumer (e.g., user, operator) of PREDICT-6G.

At the end of 2023, the project also started the development and integration activities. Led by WP4, the first step was to define the methodology (sprint based agile development and integration cycles) and timeline for developing, integrating, and validating the PREDICT-6G system components. The design of Open Labs and the structure of the validation tests have also been central in this first year. 

In conclusion, although the project is still in its infancy, we have a clear view on its merits and innovations, and the consortium is focused on achieving great impact in the industry, developing new technologies to create new deterministic networks.

by PREDICT-6G

Assessment of the first year of the project from the Partners' perspective

The PREDICT-6G consortium consists of 17 partners from seven countries working together to develop a multi-technology, multi-domain data plane that revises the reliability and time-sensitive design features existing in current wired and wireless standards. 

While we all work towards a common goal, each partner has a specific role with concrete milestones. Thus, we have asked them about the highlights of PREDICT´s first year and what they expect to achieve in 2024. 

UNIVERSIDAD CARLOS III DE MADRID

At UC3M, we have been mostly focused on developing several components of the MDP, specially on developing an open source XDP based bridge, which can be used to develop novel scheduling policies. We have also deployed multiple technologies to start building the MDP, including Wireless TSN, Ethernet-based TSN, Open Air interface 5G network, and programmable P4 switches.

During the second year of the project, through this infrastructure, we will focus on developing the WP3 components and prove the new approaches for the PREDICT-6G data plane.

ATOS

In the first year of PREDICT-6G, ATOS+ATOSP’s main focus was the design of the AI-driven Inter-domain Control-Plane (AICP). In particular, ATOS+ATOSP led the efforts related to the architecture design of the inter-domain and network control mechanisms, assuming the responsibility of defining Service Automation Management Services. Additionally, the company was an active contributor to the composition of the AI/ML layout, taking the lead in the development of the AI/ML framework, which will be used by the project as the basis for building complex AI/ML algorithms.

Looking towards PREDICT-6G second year, ATOS+ATOSP will concentrate their efforts in the implementation of the Service Automation and the AI/ML framework modules, which are considered core services for showcasing the potential of the AICP in PREDICT-6G Proof-of-Concepts (PoCs).

AUSTRALO

This year was very important for partners to build a close relationship that would underpin all the project work, including the implementation of communication and dissemination strategy. Consolidating the PREDICT-6G branding, setting up the digital tools - website and social media - and overall, positioning the project in the SNS JU, were some of the main accomplishments in the last 12 months. Moreover, AUSTRALO established the first contacts with relevant stakeholders in the SNS community with very positive results. 

In Year 2, AUSTRALO will continue to foster the PREDICT-6G community. In addition to the communication activities, the engagement with relevant stakeholders through targeted actions will accelerate to ensure the impact of the project. The dissemination of outcomes, as PREDICT-6G matures and the first results emerge, will be one of the priorities. We expect to support PREDICT-6G to become a reference in the SNS system architecture.

COGNINN

During the first year of PREDICT-6G, our main objective and area of work has been to identify security threats to predictive, multi-domain and technological 6G mobile networks, and corresponding challenges that need to be assessed through specific mechanisms and protocols. Following the completion of this work, next year we will focus on designing and developing mechanisms and protocols to provide the necessary security solutions.

CONSIGLIO NAZIONALE DELLE RICERCHE

In this first year, the CNR activities started with a comprehensive exploration of the State of the Art (SoA) in deterministic networks, with specific focus on Time-Sensitive Networking (TSN). The primary goal was to identify an effective methodology for assessing the performance of this emerging technology, particularly in terms of latency and jitter. Collaborative efforts were undertaken with all project partners to establish the architecture and define relevant case studies. In this sense, the definition of automation and robotics scenarios in line with the PREDICT-6G industrial case studies was done so as to allow gaining insight into the TSN application to information spreading and edge computing. 

Subsequently, CNR people conceptualised a sophisticated software architecture designed to evaluate latencies in both individual devices and network infrastructures, incorporating scenarios with and without running synchronisation systems. At the same time, rigorous prototype implementation and test activities were conducted to assess TSN performance over WiFi. To this regard, some preliminary results of such activities have been presented in a paper published in the Proceedings of the IEEE ETFA 2023 International Conference.

In 2024, the CNR will investigate the framework described above to assess the performance of devices and analyse the results to create virtual counterparts for use in the Digital Twin. Installing a prototype hybrid wired/wireless/5G network to conduct test campaigns on the components of the PREDICT-6G architecture.

To perform realistic simulations of sensitive scenarios to study useful scaling laws and suggest control strategies to improve performance in deterministic communication and task completion.

GESTAMP

In the first year of the project, the team dedicated their efforts to several key initiatives. A primary focus was the in-depth study and analysis of the Smart Factory use case. Internal workshops played a crucial role in establishing a first draft of the architecture framework needed for said use case. The project achieved a significant milestone with the delivery of D1.1, titled "Analysis of use case and system requirements." Additionally, the team delineated the requirements for both the Multi Data Plane (MDP) and the Control Plane.

As the project advances into its second year, the central emphasis shifts towards the design of the use case integration. This will be accompanied by the inaugural testing of the use case within the 5TONIC Open Lab. The outcomes of these tests will be documented to facilitate further experimentation and analysis in subsequent phases.

INTEL

During the first year, the Consortium helped to define the architecture and interfaces between the AI-based control plane and the data plane innovations (e.g., exploitation of new Wi-Fi features for improved determinism). This outcome was a product of a dialog between experts in determinism in the different wired and wireless domains, addressing the challenges to integrate the available options in 3GPP, IEEE and IETF standards.

The implementation and integration of technologies in the testbed such as Wi-Fi based TSN, as well as E2E and domain-specific management services such as AI-based slicing will be central in 2024. The evaluation of the target KPIs defined in the project can then be assessed.

INTERDIGITAL

Working with so many talented individuals and impactful organisations towards the definition of deterministic communications in 6G has been the highlight of the first year.

In Year 2, InterDigital will prove the novel concept of Data Unit Groups,. This extension to IP headers will allow to treat a set of packets carrying a single Application Data Unit collectively, e.g. to map the information inside the IP header extensions to PDU Set Markers in 3GPP networks or to place them into specific TSN switch queues and/or to pre-empt them if deemed necessary to guarantee their QoS constraints. This innovation will be demonstrated an Integrated Sensing and Communication use case. 5TONIC serves as the TRL4 environment to validate the proof-of-concept.

NOKIA

The first year started in-depth analysis of the technical requirements imposed by the three use cases that will be demonstrated at the end of the project and the subsequent design of the system architecture. This was a huge work that was split in two parts: one focusing on the data-plane, and another on the control/management-plane. This design resulted in a PREDICT-6G architecture that is modular, with clear separation between technology domain management and end-to-end service management, which in turn enables extendibility to any new network technology without changing end-to-end principles.

The realisation of all PREDICT-6G components and their integration into a coherent system will be the priority in 2024. The implementation work has already started on a small scale, with a few code drops delivered at the end of 2023.

POLITECNICO DI TORINO

As far as POLITO activity was concerned, the first year of the project has been marked by acquiring competence in creating seamless deterministic services across network domains, employing a blend of telecommunications standards and innovative Wi-Fi technologies, all unified under a flexible OpenAPI-driven control architecture.

The main focus of the second year will be on providing deterministic guarantees in WiFi networks by exploring the potential of a comprehensive 802.11 scheduler that incorporates time, frequency, and space dimensions, with an emphasis on dynamic adaptation to variable traffic and radio channels. The objective will be to efficiently allocate deterministic traffic while maximising throughput for other traffic, incorporating frequent scheduling updates and considering the integration of preamble puncturing for future-proofing against emerging WiFi standards.

UNIVERSITAT POLITÈCNICA DE CATALUNYA

In its inaugural year, the UPC group achieved significant milestones in different key areas: dynamic scheduling for radio resource management in mixed traffic types for private 5G networks, and AICP Management Services (MSs) to support E2E services provisioning and maintenance.

Dynamic Scheduling for Radio Resource Management in Mixed Traffic Types for Private 5G Networks involved substantial progress in the domain of dynamic scheduling and OFDMA radio resource management in the context of mixed traffic types (Isochronous TSN, Asynchronous TSN and Best Effort (BE)) within private 5G networks deployed in industrial settings. This entails the effective allocation of resources and admission control in response to the varying communication demands of diverse traffic types. The outcomes of this effort include improved spectral efficiency, reduced latency/jitter and enhanced reliability, all crucial factors for the successful integration of 5G technologies in private networks and the support of a range of applications in the industrial domain.

On the other hand, UPC actively contributed to the design and preliminary implementation of AICP MSs, such as Digital Twin for KPI evaluation and Path Computation, both at technology domain level and at the E2E level. Both MSs are essential for the deterministic services provisioning assuring their requirements and represent significant components of the PREDICT-6G AICP.   

In conclusion, the first year has been marked by commendable progress. These achievements reflect the initiative's commitment to advancing research in the field of deterministic services, laying a solid foundation for continued exploration and innovation in the months to come.

Building on the achievements of the first year, the second year of PREDICT-6G considers the following focused areas to further advance the research and development:

• Advanced Dynamic Scheduling and Resource Management in Mobility Scenarios: This involves refining and enhancing dynamic scheduling algorithms for radio resource management, placing a particular emphasis on the allocation of resources in mobility scenarios where handovers should not affect the continuity of the service. To that end, we will consider the resource allocation for the Dual Active Stack Protocol handover. We will incorporate machine learning techniques to enable the network to adapt to UL/DL traffic variability and learn from dynamic industrial environments, ensuring improved performance.
• Development and integration of a Digital Twin module for KPI evaluation as part of the AICP.
• Development and integration of a Path Computation modules as part of the AICP.  
• Integration on the Advanced Dynamic Scheduling and Resource Management in the Digital Twin: Explore the integration of the studied technologies to augment the capabilities through the integration of the schedulers in the E2E digital twin tool. Investigate how these technologies can synergize with dynamic scheduling approaches to enhance reliability, latency and real-time decision-making about the admission and rejection of traffic flows.
• Standardisation and Industry Adoption: Engage with pre-standardization bodies and industry stakeholders to contribute insights and findings to the development of 6G standards.

If you want to stay updated about PREDICT-6Gt, subscribe to our newsletter and follow us on Twitter and LinkedIn!

by PREDICT-6G

Let’s review what we have achieved, and where we are heading

By Péter Szilágyi, Technical Manager

Time flies so quickly when you are on a great team and working on an inspiring project! It feels like we have just started, yet it has been one whole year since PREDICT-6G kicked off. It has been a busy time, with lots of studies, planning, design, discussions, and deliverables. But the hard work has paid off: at the end of the year, we have created what we can claim to be a solid foundation of the project, both conceptually and practically. Let’s review what we have achieved, and what we are heading for, in more detail.

2023 summary

Looking back on the first year, it has been an intense study phase for the PREDICT-6G project. At the beginning, there were lots of questions around how to create multi-domain deterministic networks: what technologies to use, how to enable inter-working between different technological and administrative domains, and, above all, how to automate the service management in end-to-end so that it remains scalable to onboarding additional network technologies yet remains independent (as much as possible) from each technology’s specificities and limitations. We started the exploration by considering the technical requirements imposed by the three use cases that will be demonstrated at the end of the project. With this outcome-oriented methodology, we ensure that the PREDICT-6G system will be capable of delivering the needs of real-world scenarios. Based on the requirements, we designed the architecture of the system. This was a huge work that was split in two parts: one focusing on the data-plane, and another on the control/management-plane. These parts were investigated in parallel, but not at all in isolation: the idea was that data-plane technology enablers will be up-streamed and consolidated towards the control/management plane so that it can work on convenient abstractions instead of the raw controller layer of the L2/L3 technologies. This design resulted in a PREDICT-6G architecture that is modular, with clear separation between technology domain management and end-to-end service management, which in turn enables extendibility to any new network technology without changing end-to-end principles. The evolution of this work can be found in D1.1, D2.1 and D3.1, with D1.2 providing a standalone reference merging all PREDICT-6G architecture matters into a single document. Additionally, D2.2 and D3.2 provide reports on early implementation efforts, showing that PREDICT-6G no longer exists solely on paper but already now there is some code to be executed. Also, D4.1 reports on the integration plan that will bridge us over to the next year and set the next big piece of work in motion: the implementation of the PREDICT-6G system.

2024 outlook

A year’s start is just as good as the previous year’s end. That said, looking at the end of 2023 we have high hopes for 2024. Clearly, the biggest effort in 2024 will be the realisation of all PREDICT-6G components and their integration into a coherent system. The implementation work has already started on a small scale, with a few code drops delivered at the end of 2023, but the bulk of the work remains to be completed next year. Although we have a firm design and do not expect major changes to the architecture, experience shows that implementing a system for the first time never leaves the plans untouched, however carefully they were designed in the first place. Therefore, implementation is not going to be a one-way exercise, but it will evolve the thinking, understanding and design of the system as well. At the end, all will be for the benefit of the technical content that the project will deliver, so we are very much looking forward to changes rather than trying to avoid them. 

All in all, PREDICT-6G is progressing according to the project plan – it has finished all work scheduled for the first year, and has a solid foundation to become a reality in 2024. This year was rich in deliverables, having released a total of 12, exactly one per month on average. 2024 will be quieter in terms of deliverables, with only two of them scheduled; yet under this seemingly calm surface things will get rather busy in the Open Labs of Madrid and Budapest. Have a fantastic year end and stay tuned for more PREDICT-6G in 2024!

by PREDICT-6G