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

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

The project promotes also a paradigm shift from conventional Shannon-based approach, fundamentally concerned about the recovery of each transmitted bit, to a goal-oriented semantic framework, where the focus is on the recovery of the semantics underlying the transmitted message, within a goal-oriented design.
Special attention is posed on distributed machine learning strategies, running in the edge cloud, to provide delay-sensitive services with minimum energy consumption. The project includes the application of the developed novel methodologies to three use cases: aerial-assisted intelligent services, cooperative robots exploiting extended perception capabilities enabled by the edge cloud, and AI-aided extended reality.

Netwin is parte of Spoke: 8 – Intelligent and Autonomous Systems

  • The first collaborative effort of NETWIN has been the identification of the main scenarios of interest and the relative architectures. The results of this activity have been collected in the first milestone, produced at the end of June 2023.
  • NETWIN proposed novel architectures for semantic and goal-oriented communications, in order to identify and transmit only what is relevant, at the receiver side, to recover what is the semantics of the transmitted message, taking explicitly into account the goal of communication.
  • NETWIN focused also on fully automated zero-touch network architectures, with special attention to the 5G core network (5GC), working on the experimental validation of the theoretical results obtained in the first phase of the project, focusing on the implementation of microservice applications in the edge cloud.
  • NETWIN worked on distributed learning mechanisms, to be implemented in the edge cloud, with the goal of enabling low latency services and improving network efficiency.
  • An innovative semantic communication architecture, based on generative deep neural networks such as variational autoencoders and diffusion models, has been proposed and validated through simulation results. The benefits, with respect to conventional techniques, have been quantified, resulting from the capability of the decoder to regenerate the transmitted messages in case where lower data rates are used to cope, for example, with wireless channel fading. These advantages have been illustrated in a number of publications, both journal and conference papers, and in a number of invited talks.
  • The implementation of microservice applications in the edge cloud has been carried out using multi-cluster Kubernetes. The benefits of using AI models to optimize the transmission power, channel selection, and other parameters of the PHY and MAC layer have been quantified. A new cloud network flow model for the optimization of microservice applications valid for arbitrary network topologies and able to accurately compute end-to-end service latency has also been identified through the collaboration between NETWIN partners.
  • Multi-agent reinforcement learning techniques for dynamic control policies to be used for delay-constrained routing of delay-sensitive applications have been developed. Novel multi-sensor learning-based architectures for cooperative prediction and inference in partially unknown dynamical systems over sensor networks have been developed and studied. The main achievements include the development of pre-trained multi-sensor LSTM encoder-decoder models where inference is performed based on local sensor data and offline training of the prediction model while utilizing low-complexity local neural networks.
The technologies developed in NETWIN can have an impact on next generation networks to limit the energy consumption by focusing on the transmission of strictly relevant information and the exploitation of AI techniques, including both machine learning algorithms and knowledge representation. The approach followed in NETWIN is strongly methodological and then it can be applied to a variety of scenarios, such as Industry 4.0, energy, media and entertainment.
  • Università di Roma, Tor Vergata,
  • Università di Firenze
  • Università di Napoli Federico II
  • Università di Roma Sapienza
  • Fondazione Ugo Bordoni
  • Athonet
  • Dr. Eleonora Grassucci submitted a proposal for a Special Session at ICASSP 2024, Seoul, South Korea, entitled “Generative Semantic Communication: How Generative Models Enhance Semantic Communications”, that has been accepted.
  • Prof. Antonia Tulino gave a plenary talk entitled “A service-driven network evolution: from communication, to content distribution, to ubiquitous computation’’, at the IEEE International Symposium on Information Theory, June 30th, 2023.
  • Prof. Sergio Barbarossa gave an Invited talk entitled "Semantic and Goal-Oriented Communications: From Adaptive Generative Models to Optimal Resource Allocation", at the Huawei Strategy and Technology Workshop, Munich, Oct. 26th, 2023.
  • Expected: >= 36 publications in 36 months
  • Accomplished: 15 (7 journal publications + 8 conference publications)
  • Readiness: 100%
Joint Publications
  • Expected: >=12 (30% joint publications in 36 months)
  • Accomplished: 0
  • Readiness: 0% (joit collaborations have just started, joint publications will follow)
Talks/Communication events
  • Expected: 10 talks or event chairing/organizing within NETWIN activities in 36 months
  • Accomplished: > 10 (5 invited talks, 1 special session at IEEE ICASSP 2024, 2 talks at RESTART General Meetings, and 5 conference presentations)
  • Readiness: >100%
  • Expected: 3 PoCs expected by the end of the project
  • Accomplished: 0
  • Readiness: 0% (work according to plan)
Project Meetings
  • Expected: > 12 meetings
  • Accomplished: 3 whole project meetings + specific WPs' meetings
  • Readiness:100%
  • Expected: 3 items over 36 months
  • Accomplished: 0 items submitted to mission 7
  • Readiness: 0%

Collaboration proposals
Given its methodological imprint, NETWIN is fully open to collaborations and it has already identified the following collaborations with other two other RESTART projects: 6GWINET and SUPER.
In the first phase of the project, NETWIN has collaborated with Spoke 8 to develop a joint strategy for the acquisition of instrumentations to be used for the project, such as a private 5G network. Furthermore, NETWIN has worked with Spoke 8 to set up the cascade calls useful to include new partners having specific expertise on the technologies involved in NETWIN proofs of concept.

For any proposal of collaboration within the project please contact sergio.barbarossa at

Netwin News: