Tesi etd-02052024-161013 |
Link copiato negli appunti
Tipo di tesi
Tesi di laurea magistrale
Autore
GHADIR, DELARAM
URN
etd-02052024-161013
Titolo
Dynamic tunnel Selection in SD-WAN using PPO-Based Reinforcement Learning
Dipartimento
INFORMATICA
Corso di studi
INFORMATICA E NETWORKING
Relatori
relatore Adami, Davide
relatore Borgianni, Luca
relatore Borgianni, Luca
Parole chiave
- delay minimization
- link selection
- Proximal Policy Optimization (PPO) Algorithm
- reinforcement learning
- software-defined wide area networking
Data inizio appello
23/02/2024
Consultabilità
Non consultabile
Data di rilascio
23/02/2027
Riassunto
The thesis focuses on deploying an software-defined wide area network (SD-WAN) featuring LTE, MPLS, and Satellite tunnels. Using the Proximal Policy Optimization (PPO) algorithm in reinforcement learning, the study aims to enhance network performance by minimizing delays. The simulation, conducted with Python and Mininet, assesses the ability to intelligently select optimal links based on criteria such as bandwidth and delay satisfaction
File
| Nome file | Dimensione |
|---|---|
La tesi non è consultabile. |
|