The Networked Systems research group, led by Prof. Francesco Delli Priscoli and Prof. Antonio Pietrabissa, aims at developing control methodologies in or over networked systems. Besides classical control methods, such as model predictive control, optimal control and robust control, distributed non-cooperative control methods are being developed on the ground of mean-field game theory as well as learning methodologies such as reinforcement learning and deep reinforcement learning.
The Networked Systems research group has developed thanks to the successful participation in National and European research projects carried on together with major European ICT and energy players.
The networked systems area supports a Future Internet vision (in particular, the Networked Systems research group participated to the large FI-WARE EU project concerning the Future Internet technology foundation) foreseeing a technology independent distributed framework including coordinated advanced control algorithms (utilizing methodologies such as reinforcement learning for multi-agent systems, game theory, optimal control, model predictive control and robust control). These algorithms, on the basis of homogeneous integrated metadata (derived from properly selected heterogeneous information related to the present network and user status, converted to metadata and aggregated in a context-aware fashion), make consistent decisions (which are eventually actuated in the networks) concerning the management of network resources and of network contents/services, aiming at maximizing resource exploitation while satisfying users in terms of Quality of Experience expectations (related to Quality of Service, security and mobility requirements).
To deal with the above-mentioned vision, the Networked Systems area deals with the following key enablers: model-free learning, multi-agent systems with minimum coordination, cross-layering/cross-network optimization, context awareness, data fusion, decision support systems.
In the framework of recent and in-progress projects, the above-mentioned vision has been applied in the following areas: home network speed enhancement up to Gbps, optimization of hybrid ad hoc and satellite networks, resource management for telecommunication and energy distribution networks (smart grids), demand side management for planning electric utilities, smart grids for supporting fully electrical vehicles, content management for peer-to-peer television, protection of critical infrastructures, total airport security, embedded system security/privacy/dependability, remote diagnosis and management of cardiovascular diseases, intermodal mobility solutions for people and goods, space assets for demining assistance, wireless cognitive sensor networks.
In 2013, the Sapienza Start Up Ares2t was funded by members of the Networked System group on the ground of the researches in the field of smart grids.
Recent and on-going projects
- 5G-SOLUTIONS, 5G Solutions for European Citizens (managed by CRAT), June 2019-May 2022, EU H2020-ICT-2019 Project.
- SESAME, Smart European Space Access thru Modern Exploitation of Data Science (managed by CRAT), January 2015 - December 2022, EU H2020-SPACE-16-TEC-2018 Project.
- 5G-ALLSTAR, 5G AgiLe and fLexible integration of SaTellite And cellular (managed by CRAT), July 2018-June 2021, H2020-EUK2018 Project.
- ATENA, Advanced Tools to assEss and mitigate the criticality of ICT compoNents and their dependencies over Critical InfrAstructures (managed by CRAT), May 2016-April 2019, EU MG H2020 Project.
- Bonvoyage, From Bilbao to Oslo, intermodal mobility solutions and interfaces for people and goods, supported by an innovative communication network (managed by CRAT), May 2015-April 2018-EU DS H2020 Project.
- PROMETEO, Protezione di reti elettriche di potenza da attacchi cyber-fisici mediante strategie di controllo, progetto di Ateneo, prot. RM11715C7EFAF857.