S
Sebastian Troia
Researcher at Polytechnic University of Milan
Publications - 47
Citations - 542
Sebastian Troia is an academic researcher from Polytechnic University of Milan. The author has contributed to research in topics: Computer science & Software-defined networking. The author has an hindex of 9, co-authored 30 publications receiving 259 citations.
Papers
More filters
Journal ArticleDOI
Matheuristic with machine-learning-based prediction for software-defined mobile metro-core networks
TL;DR: A matheuristic for dynamic optical routing is introduced, which can be implemented as an application into a software-defined mobile carrier network and used to solve off-line mixed-integer linear programming instances of an optical routing (and wavelength) assignment optimization problem.
Proceedings ArticleDOI
Network Traffic Prediction based on Diffusion Convolutional Recurrent Neural Networks
Davide Andreoletti,Sebastian Troia,Francesco Musumeci,Silvia Giordano,Guido Maier,Massimo Tornatore +5 more
TL;DR: This paper employs a recently-proposed graph-based ML algorithm, the Diffusion Convolutional Recurrent Neural Network (DCRNN), to forecast traffic load on the links of a real backbone network, and evaluates DRCNN's ability to forecast the volume of expected traffic and to predict events of congestion.
Proceedings ArticleDOI
Deep Learning-Based Traffic Prediction for Network Optimization
TL;DR: This work investigated a particular type of RNN, the Gated Recurrent Units (GRU), able to achieve great accuracy, and used the predictions to dynamically and proactively allocate the resources of an optical network.
Journal ArticleDOI
Machine Learning-Based Routing and Wavelength Assignment in Software-Defined Optical Networks
Ignacio Martin,Sebastian Troia,José Alberto Hernández,Alberto Rodriguez,Francesco Musumeci,Guido Maier,Rodolfo Alvizu,Oscar Gonzalez de Dios +7 more
TL;DR: Numerical results show that near-optimal RWA can be obtained with the ML approach, while reducing computational time up to 93% in comparison to a traditional optimization approach based on integer linear programming.
Journal ArticleDOI
Reinforcement Learning for Service Function Chain Reconfiguration in NFV-SDN Metro-Core Optical Networks
TL;DR: This article investigates the application of Reinforcement Learning (RL) for performing dynamic SFC resources allocation in NFV-SDN enabled metro-core optical networks and builds an RL system able to optimize the resources allocation of SFCs in a multi-layer network.