Periodic Reporting for period 1 - 5G-IANA (5G Intelligent Automotive Network Applications)
Période du rapport: 2021-06-01 au 2023-02-28
5G-IANA aims at providing an open 5G experimentation platform, on top of which third-party experimenters, i.e. SMEs in the Automotive vertical sector will have the opportunity to develop, deploy and test their services. The provided Automotive Open Experimentation Platform (AOEP) is a set of hardware and software resources that provides the computational and communication/transport infrastructure as well as the management and orchestration components, coupled with an enhanced nApp Toolkit tailored to the Automotive sector, for simplifying the design and onboarding of new nApps. 5G-IANA exposes to experimenters secured and standardized Application Programming Interfaces (APIs) for facilitating all the different steps towards the production stage of a new service. 5G-IANA targets different virtualization technologies integrating different Management and Orchestration (MANO) frameworks for enabling the deployment of end-to-end network services across different segments (vehicles, road infrastructure, Multi-access Edge Computing (MEC) nodes and cloud resources). 5G-IANA nApp toolkit is linked with an Automotive Virtual Network Functions (VNFs) Repository including an extensive portfolio of ready-to-use and openly accessible Automotive-related VNFs and nApp templates, that are available for SMEs to use and develop new applications. Finally, 5G-IANA develops a Distributed Machine Learning (DML) framework, that provides functionalities for simplified management and orchestration of collections of Machine Learning (ML) service components and thus, allows ML-based applications to penetrate the Automotive world, due to its inherent privacy-preserving nature. 5G-IANA will be demonstrated through seven Automotive-related use cases in two 5G Stand Alone (SA) testbeds. Moving beyond technological challenges, and exploiting input from the demonstration activities, 5G-IANA will identify and validate market conditions for innovative, yet sustainable business models for the AOEP platform, supporting a long-term roadmap towards the pan-European deployment of 5G as a key advanced Automotive services enabler.
The project objectives are :
- Specify and provide an Automotive Open Experimental Platform (AOEP)
- Specify and implement a repository environment for nApps and VNFs to ease the design and chaining of new Automotive-related services
- Ensure co-existence with DSRC and LTE/5G and enhance network platform performances for the Automotive vertical
- Provide accurate localization and low latency mission-critical applications
- Define, implement and trial Connected and Automated Driving relevant Use Cases to validate and assess the AOEP suitability and functional improvements
- Improve service creation time (5G-PPP KPI)
- Create new business opportunities and boost market for start-ups and SMEs with Automotive NetApps
- Increase road safety by leveraging Connected and Automated Mobility using enhanced network performances
- Ensure cross-domain and cross-platform interoperability and boost standardisation committees on NFV and Network orchestration
The project objectives are :
- Specify and provide an Automotive Open Experimental Platform (AOEP)
- Specify and implement a repository environment for nApps and VNFs to ease the design and chaining of new Automotive-related services
- Ensure co-existence with DSRC and LTE/5G and enhance network platform performances for the Automotive vertical
- Provide accurate localization and low latency mission-critical applications
- Define, implement and trial Connected and Automated Driving relevant Use Cases to validate and assess the AOEP suitability and functional improvements
- Improve service creation time (5G-PPP KPI)
- Create new business opportunities and boost market for start-ups and SMEs with Automotive NetApps
- Increase road safety by leveraging Connected and Automated Mobility using enhanced network performances
- Ensure cross-domain and cross-platform interoperability and boost standardisation committees on NFV and Network orchestration
- Identification of the AOEP functional requirements, at platform level and at component level.
- Detailed design of the overall AOEP architecture including module and interfaces definitions for the support of the functional requirements.
- Extraction of platform- and module-level specifications, feeding the development activities.
- Extraction of detailed technical design processes: i) Definition of the end user interface with the platform and the toolkit, and the process for nApp onboarding, modification, deployment, monitoring selection and policy rule enforcement, ii) Definition of the NOD-SM-MSO workflow for the deployment of the requested nApps, the collection of monitoring data from deployed nApps, the feeding of location information to NOD, the implementation of policy based nApp reconfiguration loop, iii) Definition of the OBU/Edge/Core continuum interconnection with the AOEP including the resource inventory interfacing with the multi-domain orchestrator, iv) Definition of the DML framework functionalities.
- Development and initial integration of key AOEP building blocks required towards the integrated cycle A release and the complete onboarding and deployment of nApps.
- Identification of the best suitable metamodel language to describe and store nApps and AFs/NFs, and definition of the arguments necessary to fully describe a nApp.
- Definition of the APIs to be provided to the users and the APIs to be developed for internal use only.
- Components’ development and initial integration for providing a full end-to-end nApp-workflow from the design of a nApp composed through atomic components stored in the centralized registry, the chaining and the packaging of these components into a nApp, the onboarding on the catalogue, and the deployment on a 5G environment.
- AFs and NFs that will form the nApps are under development (39 AFs, 23 NFs and 22 nApps).
- All 7 5G-IANA use cases have identified their KPIs to be tested, as well as the testing methodology to be followed per KPI.
- The project has completed a survey collecting the third party expectations from the 5G-IANA platform.
- The project has launched its first Open Call inviting SMEs to implement and trial their own nApps/UCs on the platform.
- Detailed design of the overall AOEP architecture including module and interfaces definitions for the support of the functional requirements.
- Extraction of platform- and module-level specifications, feeding the development activities.
- Extraction of detailed technical design processes: i) Definition of the end user interface with the platform and the toolkit, and the process for nApp onboarding, modification, deployment, monitoring selection and policy rule enforcement, ii) Definition of the NOD-SM-MSO workflow for the deployment of the requested nApps, the collection of monitoring data from deployed nApps, the feeding of location information to NOD, the implementation of policy based nApp reconfiguration loop, iii) Definition of the OBU/Edge/Core continuum interconnection with the AOEP including the resource inventory interfacing with the multi-domain orchestrator, iv) Definition of the DML framework functionalities.
- Development and initial integration of key AOEP building blocks required towards the integrated cycle A release and the complete onboarding and deployment of nApps.
- Identification of the best suitable metamodel language to describe and store nApps and AFs/NFs, and definition of the arguments necessary to fully describe a nApp.
- Definition of the APIs to be provided to the users and the APIs to be developed for internal use only.
- Components’ development and initial integration for providing a full end-to-end nApp-workflow from the design of a nApp composed through atomic components stored in the centralized registry, the chaining and the packaging of these components into a nApp, the onboarding on the catalogue, and the deployment on a 5G environment.
- AFs and NFs that will form the nApps are under development (39 AFs, 23 NFs and 22 nApps).
- All 7 5G-IANA use cases have identified their KPIs to be tested, as well as the testing methodology to be followed per KPI.
- The project has completed a survey collecting the third party expectations from the 5G-IANA platform.
- The project has launched its first Open Call inviting SMEs to implement and trial their own nApps/UCs on the platform.
Progress beyond current state of the art:
- Proposal of a novel data-model for representing Automotive services that ease the nApp chaining by exposing to the user only the high-level information needed for building an end-to-end service, hiding at the same time the network complexity.
- Work towards designing and developing a federated learning orchestration framework including: i) monitoring mechanisms at discrete resource and data levels, ii) model and data transfer mechanisms, iii) decision making mechanisms that orchestrate the federated learning process with support for intelligent client selection, and iv) integrated operation within network MANO solution.
- Progress on the development of the “on-vehicle MANO”; the platform is being designed to support the deployment and broader lifecycle management of AFs/NFs on both the edge and the far-edge segments (OBUs).
Expected results and impacts:
- 5G-IANA is going to provide a full-fledged platform along with a set of AFs/NFs, tools and predefined nApps that will make easier for SMEs and start-ups to design and create their own applications on top of the provided platform. It is expected that this will lower the barriers to market entry. The techno-economic analysis and sustainability study of respective business models will further foster this activity.
- With respect to societal impact, 5G-IANA is foreseen to provide increased safety through the design and validation of services and AFs/NFs related to manoeuvre planning, vehicle condition warning, object detection, remote driving central control, and hazardous driving behaviour detection, among others. Such functionalities enable the delivery of real-time notifications on the vehicles related to emergency cases or to hazardous driving behaviour detection or to safer coordination of traffic in cross-roads, or enable the sharing of information about emergency incidents to public authorities. Additionally, the predictive QoS aspect of the project delivers a functional enabler promoting road safety, by allowing services safely adjust their functionality to the fluctuating network conditions in a proactive manner.
- Proposal of a novel data-model for representing Automotive services that ease the nApp chaining by exposing to the user only the high-level information needed for building an end-to-end service, hiding at the same time the network complexity.
- Work towards designing and developing a federated learning orchestration framework including: i) monitoring mechanisms at discrete resource and data levels, ii) model and data transfer mechanisms, iii) decision making mechanisms that orchestrate the federated learning process with support for intelligent client selection, and iv) integrated operation within network MANO solution.
- Progress on the development of the “on-vehicle MANO”; the platform is being designed to support the deployment and broader lifecycle management of AFs/NFs on both the edge and the far-edge segments (OBUs).
Expected results and impacts:
- 5G-IANA is going to provide a full-fledged platform along with a set of AFs/NFs, tools and predefined nApps that will make easier for SMEs and start-ups to design and create their own applications on top of the provided platform. It is expected that this will lower the barriers to market entry. The techno-economic analysis and sustainability study of respective business models will further foster this activity.
- With respect to societal impact, 5G-IANA is foreseen to provide increased safety through the design and validation of services and AFs/NFs related to manoeuvre planning, vehicle condition warning, object detection, remote driving central control, and hazardous driving behaviour detection, among others. Such functionalities enable the delivery of real-time notifications on the vehicles related to emergency cases or to hazardous driving behaviour detection or to safer coordination of traffic in cross-roads, or enable the sharing of information about emergency incidents to public authorities. Additionally, the predictive QoS aspect of the project delivers a functional enabler promoting road safety, by allowing services safely adjust their functionality to the fluctuating network conditions in a proactive manner.