Project description
AI-driven 6G with data and testing solutions
6G technology requires AI and machine learning to work seamlessly across all parts of the system, from network management to resource optimisation. However, there are several challenges. One issue is the lack of high-quality datasets needed to train AI models. Additionally, testing and evaluating AI models in a real 6G environment is difficult without access to a testbed or digital twin. In this context, the EU-funded 6G-DALI project will create an end-to-end AI framework for 6G. It has two main components: AI experimentation as a service and data collection and storage. This framework provides data for training and easy access to open datasets. It also includes a digital twin testbed for generating data on demand.
Objective
One of the key enablers of 6G is undoubtedly the Native support of AI/ML at all the system levels, components, and mechanisms, from the orchestration and management levels to the low-level optimization of the infrastructure resources, including Cloud, Edge, RAN, Core Network, as well as a transport network. Despite the opportunities, there are several gaps that hinder the adoption of AI/ML in 6G, such as the lack of extensive and high-quality datasets that are required to train the models. On the other hand, AI model testing and performance evaluation in a representative staging environment (by emulation or real deployment) is also challenging without access to an end-to-end 6G testbed or representative Digital Twin environment. To this end, 6G-DALI aims to deliver an end-to-end AI framework for 6G, structured in two interdependent pillars, (1) AI experimentation as a service via MLOps and (2) Data and analytics collection and storage via DataOps. The 6G-DALI DataOps pillar provides the mechanisms for preparing clean and processed data that are stored within a 6G Dataspace and are made available for training and validating machine learning models as a service, a part of the MLOps Pillar. The end-to-end framework also delivers continuous monitoring, drift detection and retraining of models. Finally, 6G-DALI will deliver open datasets, a 6G Dataspace for dataset storage and secure sharing, and a Digital Twin testbed for data generation on demand.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques.
You need to log in or register to use this function
Programme(s)
- HORIZON.2.4 - Digital, Industry and Space Main Programme
Topic(s)
Funding Scheme
HORIZON-JU-RIA - HORIZON JU Research and Innovation ActionsCoordinator
151 25 Maroussi
Greece