NETWIN

NETWIN (Network Intelligence) is a structural project supported by the National Recovery and Resilience Plan (NRRP) funded by Next Generation EU program. NETWIN is a structural project, coordinated by Prof. Sergio Barbarossa, included in the national project RESTART (RESearch and innovation on future Telecommunications systems and networks, to make Italy more smART), which started on January 1st, 2023 and it has a duration of three years.

The goal of NETWIN is to leverage the synergism between artificial intelligence and networks in two directions: 

i) design machine learning strategies that will guide the design of autonomous networks able to efficiently handle the complexity of the telecommunications of the future with minimum human intervention; 

ii) design network architectures able to promote the pervasive deployment of delay-sensitive and energy-constrained intelligent services. 

The project promotes a paradigm shift from conventional Shannon-based approach, fundamentally concerned about the reliable recovery of the transmitted bit, to a semantic and goal-oriented approach, that leverage advanced knowledge representation systems and generative artificial intelligence to make the exchange of information more efficient and tailored to the task to be accompliched.

Special attention is posed on distributed machine learning strategies, running in the edge cloud, to provide delay-sensitive services with minimum energy consumption. A further focus is the delivery of intelligent services on demand, so that learning mechanisms are brought closer to the end users where and when needed, using aerial-assisted vehicles or enabling a cost-efficient interaction between moving vehicles and edge servers. The project includes the development of three proofs of concept: 

• AI-aided moving robots offloading computation to the edge cloud

• on demand intelligent services using unmanned aerial vehicles interacting with a digital twin on the ground

• holographic virtual assistant with advanced conversational capabilities