Towards network optimization using graph neural networks
Network modeling is a critical component for building self-driving Software-Defined Networks.Traditional modeling solutions,such as simulation,are insufficient as they need a long time to run the simulations.We study how GNN models can help to solve network optimization problems such as routing.
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2019 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/175656 |
| Acceso en línea: | https://hdl.handle.net/2117/175656 |
| Access Level: | acceso abierto |
| Palabra clave: | Neural networks (Computer science) Machine learning Graph Neural Networks Software Defined Networking Deep Reinforcement Learning Optimization Xarxes neuronals (Informàtica) Aprenentatge automàtic Àrees temàtiques de la UPC::Informàtica |
| Sumario: | Network modeling is a critical component for building self-driving Software-Defined Networks.Traditional modeling solutions,such as simulation,are insufficient as they need a long time to run the simulations.We study how GNN models can help to solve network optimization problems such as routing. |
|---|