• español
    • English
  • Login
  • español 
    • español
    • English
  • Tipos de Publicaciones
    • bookbook partconference objectdoctoral thesisjournal articlemagazinemaster thesispatenttechnical documentationtechnical report
Ver ítem 
  •   IMDEA Networks Principal
  • Ver ítem
  •   IMDEA Networks Principal
  • Ver ítem
JavaScript is disabled for your browser. Some features of this site may not work without it.

DUNE: Distributed Inference in the User Plane

Compartir
Ficheros
DUNE_INFOCOM25_DSpace.pdf (1.107Mb)
Identificadores
URI: https://hdl.handle.net/20.500.12761/1883
Metadatos
Mostrar el registro completo del ítem
Autor(es)
Bütün, Beyza; de Andrés Hernández, David; Gucciardo, Michele; Fiore, Marco
Fecha
2025-05
Resumen
The deployment of Machine Learning (ML) models in the user plane enables line-rate in-network inference, significantly reducing latency and improving the scalability of functions like traffic monitoring. Yet, integrating ML models into programmable network devices requires meeting stringent constraints in terms of memory resources and computing capabilities. Previous solutions have focused on implementing monolithic ML models within individual programmable network devices, which are limited by hardware constraints, especially while executing challenging classification use cases. In this paper, we propose DUNE, a novel framework that realizes for the first time a user plane inference that is distributed across the multiple devices that compose the programmable network. DUNE adopts fully automated approaches to (i) breaking large ML models into simpler sub-models that preserve inference accuracy while minimizing resource usage, (ii) designing the sub-models and their sequencing so as to enable an efficient distributed execution of joint packet- and flow-level inference. We implement DUNE using P4, deploy it in an experimental network with multiple industry-grade programmable switches, and run tests with real-world traffic measurements for two complex classification use cases. Our results demonstrate that DUNE not only reduces per-switch resource utilization with respect to legacy monolithic ML designs but also improves their inference accuracy by up to 7.5%.
Compartir
Ficheros
DUNE_INFOCOM25_DSpace.pdf (1.107Mb)
Identificadores
URI: https://hdl.handle.net/20.500.12761/1883
Metadatos
Mostrar el registro completo del ítem

Listar

Todo IMDEA NetworksPor fecha de publicaciónAutoresTítulosPalabras claveTipos de contenido

Mi cuenta

Acceder

Estadísticas

Ver Estadísticas de uso

Difusión

emailContacto person Directorio wifi Eduroam rss_feed Noticias
Iniciativa IMDEA Sobre IMDEA Networks Organización Memorias anuales Transparencia
Síguenos en:
Comunidad de Madrid

UNIÓN EUROPEA

Fondo Social Europeo

UNIÓN EUROPEA

Fondo Europeo de Desarrollo Regional

UNIÓN EUROPEA

Fondos Estructurales y de Inversión Europeos

© 2021 IMDEA Networks. | Declaración de accesibilidad | Política de Privacidad | Aviso legal | Política de Cookies - Valoramos su privacidad: ¡este sitio no utiliza cookies!