Presenter: Guido Marchetto and Alessio Sacco
Wednesday, June 8th, 2022 17:00
Location: SmartData@Covivio
Recent management and orchestration approaches for softwarized networks employ Artificial Intelligence (AI) and Machine Learning (ML) to further reduce reaction time and improve the accuracy of decisions, while automating network operations to ultimately facilitate the deployment of new interactive services.
In this talk, we present a novel class of software network solutions that share the goal of enabling intelligent and autonomous computer networks, exploring how to exploit the power of AI/ML to handle the growing complexity of these emerging applications, with particular focus on critical systems, such as industrial networks or telemedicine frameworks. We start with routing and network planning, proposing a network management schema that auto-scales (virtual) network resources to accommodate the traffic demand and reacts to possible failures.
Then, acting on TCP congestion control, we propose an ML-based solution aiming to solve the problem of an adequate congestion window update strategy that can increase the throughput and fairness while reducing the number of packet losses and delays.
Biography:
Guido Marchetto received the Ph.D. degree in computer engineering from the Politecnico di Torino, in 2008, where he is currently an Associate Professor with the Department of Control and Computer Engineering. In 2009, he visited the Department of Computer Science at Boston University. His research topics focus on learning-based solutions for network management and on formal verification of security and safety policies in distributed systems. His interests also include network protocols and network architectures. He is Senior Member of the IEEE.
Alessio Sacco received the M.Sc. degree in Computer Engineering from the Politecnico di Torino, where he is currently pursuing the Ph.D. degree in Computer Engineering. His research interests include architecture and protocols for network management; implementation and design of cloud computing applications; algorithms and protocols for service-based architecture, such as Software Defined Networks (SDN), used in conjunction with Machine Learning algorithms.