A benchmark for graph neural networks for computer network modeling

View/Open
Cita com:
hdl:2117/168587
Document typeMaster thesis
Date2019-06-27
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder
Abstract
Today, network operators still lack functional network models able to make accurate predictions of end-to-end Key Performance Indicators (e.g., delay).This thesis introduces the benchmark for computer network modeling using the RouteNet Graph Neural Network as well as a routing creation algorithm.
SubjectsGraph theory, Machine learning, Neural networks (Computer science), Grafs, Teoria de, Aprenentatge automàtic, Xarxes neuronals (Informàtica)
DegreeMÀSTER UNIVERSITARI EN INNOVACIÓ I RECERCA EN INFORMÀTICA (Pla 2012)
Files | Description | Size | Format | View |
---|---|---|---|---|
143477.pdf | 3,481Mb | View/Open |