Recent advances in Machine Learning (ML) brought several advantages also within computer network management. For programmable data planes, however, it is more challenging to benefit from these advantages, given their limited resource capabilities colliding with the complexity of ML models. In this paper, we propose ART, an attempt to simplify ML-based solutions for routing, so that they can "fit", i.e., be executed, on P4 switches. To provide such model simplification, ART relies on efficient knowledge distillation techniques, converting, in particular, Deep Reinforcement Learning (DRL) models into a simpler Decision Tree (DT). Our evaluation results validate the accuracy of the extracted model and the application of the model logic directly into switches with little impact, paving the way for a more reactive data plane programmability via machine learning integration.

Routing with ART: Adaptive Routing for P4 Switches With In-Network Decision Trees / Angi, Antonino; Sacco, Alessio; Esposito, Flavio; Marchetto, Guido. - ELETTRONICO. - (In corso di stampa). (Intervento presentato al convegno 2024 IEEE Global Communications Conference (GLOBECOM) tenutosi a Cape Town (ZA) nel 8 - 12 December 2024).

Routing with ART: Adaptive Routing for P4 Switches With In-Network Decision Trees

Angi, Antonino;Sacco, Alessio;Marchetto, Guido
In corso di stampa

Abstract

Recent advances in Machine Learning (ML) brought several advantages also within computer network management. For programmable data planes, however, it is more challenging to benefit from these advantages, given their limited resource capabilities colliding with the complexity of ML models. In this paper, we propose ART, an attempt to simplify ML-based solutions for routing, so that they can "fit", i.e., be executed, on P4 switches. To provide such model simplification, ART relies on efficient knowledge distillation techniques, converting, in particular, Deep Reinforcement Learning (DRL) models into a simpler Decision Tree (DT). Our evaluation results validate the accuracy of the extracted model and the application of the model logic directly into switches with little impact, paving the way for a more reactive data plane programmability via machine learning integration.
In corso di stampa
File in questo prodotto:
File Dimensione Formato  
ART___Globecom.pdf

accesso aperto

Descrizione: Manuscript accepted
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 327.59 kB
Formato Adobe PDF
327.59 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2991306