Machine-Learning Defined Networking: how Artificial Intelligence is enabling Network Softwarization
Software Defined Networking (SDN) and Network Function Virtualization (NFV) are the emerging technologies brought by the new trend commonly referred to as Network Softwarization (SN). SN is automating networks, reducing CapEx and OpEx for the Communication Service Providers (CSPs) and boosting innovation. This particularly applies to network control, management and configuration, for which programmability opens great opportunities introducing increasingly smart algorithms to optimize the IT and network resources. In this context, Artificial Intelligence (AI), and more specifically Machine Learning (ML), has become an incredibly fruitful methodology. ML allows to implement new functions such as traffic prediction and classification, identification of faults, predictive maintenance, scheduling of investments, performance routing, etc. with a reasonable level of complexity. On the opposite, with non-AI approaches, such functions – when feasible – would have required unmanageable complexity. This keynote shows how AI can efficiently optimize resources in 5G metro-core SDN/NFV networks. In particular, we have selected a set of use-cases from our recent research activity, each one demonstrating the application of a different ML “flavor” (i.e. supervised, unsupervised, reinforcement, etc.). The goal is to provide suggestions to the modern CSPs on how to exploit AI to generate intelligent and dynamic optimization tools to face the challenges posed by the softwarization age.
Sebastian Troia (Member, IEEE) received the Ph.D. degree (cum laude) in information technology from the Politecnico di Milano, Italy, in 2020. He is currently an Assistant Professor with the Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano. He has coauthored more than 30 publications in international journals, conferences, and book chapters with particular attention to the context of machine-learning for SDN, SD-WAN, and NFV. His current research interests include in the field of edge networks softwarization and machine-learning for communication networks. His activities comprise the development of intelligent control and orchestration plane architectures for SDN and SD-WAN in multi-layer (optical and IP) networks scenarios. He was involved in different European Projects: H2020 Metro-Haul, NGI Atlantic, and FP7 Marie Curie MobileCloud, and served as an Editor for the ITU Focus Group on Machine Learning for Future Networks, including 5G (FG-ML5G). He is the Co-Organizer and the Technical Program Committee (TPC) Co-Chair of the 1st International Workshop on Edge Network Softwarization (ENS 2022), co- located with NetSoft 2022. He serves as a reviewer for several international journals and TPC of international conferences and workshops.
Guido Maier received his Laurea degree in Electronic Engineering at Politecnico di Milano (Italy) in 1995 and his Ph.D. degree in Telecommunication Engineering at the same university in 2000. Until February 2006 he has been researcher at CoreCom (research consortium supported by Pirelli in Milan, Italy), where he achieved the position of Head of the Optical Networking Laboratory. On March 2006 he joined the Politecnico di Milano as Assistant Professor. In 2015 he became Associate Professor. His main areas of interest are: optical network modeling, design and optimization; SDN orchestration and control-plane architectures; SD-WAN and NFV. He is author of more than 150 papers in the area of Networking published in international journals and conference proceedings (h-index 25) and 6 patents. He is currently involved in industrial and European research projects. In 2016 he co-founded the start-up SWAN networks, spin-off of Politecnico di Milano. He is editor of the journal Optical Switching and Routing, General Chair of DRCN 2020, DRCN 2021 and NetSoft 2022, guest editor of a special issue of the IEEE Open Journal of the Communications Society and TPC member in many international conferences. He is a Senior Member of the IEEE Communications Society.