AI@EDGE

Description

i2CAT participates in AI@EDGE, one of the 9 research projects retained from the 81 proposals submitted to the European Commission in response to the 5G-PPP ICT-52-2020 call: 5G-PPP Smart Connectivity beyond 5G. The project, started in January 2021, lasts 3 years and involves 19 partners among industries, universities and research institutes from 8 countries.

Artificial Intelligence has become a major innovative force, and it is one of the pillars of the fourth industrial revolution. While significant progress has been made during the last years concerning AI-enabled platforms’ accuracy and performance, their integration in potentially autonomous decision-making systems or even critical infrastructures requires assuring end-to-end quality. The goal of the H2020 AI@EDGE is to address this issue by introducing reusable, secure and trustworthy AI solutions in the Network Edge. AI@EDGE aims to revolutionise communication networks achieving an EU-wide impact on industry-relevant aspects of the AI-for-networks and networks-for-AI paradigms in beyond 5G systems, with a variety of applications including vehicles, industrial networks, aviation and in-flight entertainment.

Estimated impact

AI@EDGE targets significant breakthroughs in two fields:

• General-purpose frameworks for closed-loop network automation capable of supporting flexible and programmable pipelines for the creation, utilization, and adaptation of the secure, reusable, and trustworthy AI/ML models
• Definition of a converged Connect Compute platform for creating and managing resilient, elastic, and secure end-to-end slices capable of supporting a diverse range of AI-enabled network applications.

The introduction of AI and Machine Learning (ML) technologies in the cloud-network convergence process will be crucial and help operators achieve a higher level of automation, increase network performance, and decrease the time-to-market of new features.

The results of AI@EDGE will be validated against four use cases with specific requirements that cannot be satisfied by current 5G networks: (1) Connected and Automated Mobility, (2) Industrial IoT, (3) In-Flight Entertainment, and (4) Industrial Operations-oriented UAV. Ultra-low latency, secure communication, connectivity, resilience, and service continuity under mobile conditions are some of the prominent challenges that the AI@EDGE Use Cases will address.

I2CAT leads T4.1 on the design of the Connect-Compute Platform, which is the joint point of the project’s innovations by enabling secure and automated roll-out of large-scale edge and cloud compute infrastructures. In addition, i2CAT will have a significant role in the definition of the architecture for closed-loop network automation, the design of solutions for multi-connectivity and disaggregated RANs, and the alignment with the O-RAN architecture.