Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A network architecture for scalable end-to-end management of reusable AI-based applications

Brito, Flavio ; Cisneros, Josue Castaneda ; Linder, Neiva ; Riggio, Roberto ; Coronado, Estefania ; Palomares, Javier ; Adzic, Jovanka ; Renart, Javier ; Lindgren, Anders and Rosa, Miguel , et al. (2023) 14th International Conference on Network of the Future, NoF 2023 In Proceedings of the 14th International Conference on Network of the Future, NoF 2023 p.98-102
Abstract

Artificial intelligence (AI) is a key enabler for future 6G networks. Currently, related architecture works propose AI-based applications and network services that are dedicated to specific tasks (e.g., improving the performance of RAN with AI). These proposed architectures offer a unique way to collect data, process it, and extract features from data for each AI-based application. However, this dedicated approach creates AI-silos that hinder the integration of AI in the networks. In other words, such AI-silos create a set of AI-models and data for AI-based applications that only work within a single dedicated task. This single-task approach limits the end-to-end integration of AI in the networks. In this work, we propose a network... (More)

Artificial intelligence (AI) is a key enabler for future 6G networks. Currently, related architecture works propose AI-based applications and network services that are dedicated to specific tasks (e.g., improving the performance of RAN with AI). These proposed architectures offer a unique way to collect data, process it, and extract features from data for each AI-based application. However, this dedicated approach creates AI-silos that hinder the integration of AI in the networks. In other words, such AI-silos create a set of AI-models and data for AI-based applications that only work within a single dedicated task. This single-task approach limits the end-to-end integration of AI in the networks. In this work, we propose a network architecture to deploy AI-based applications, at different network domains, that prevents AI-silos by offering reusable data and models to ensure scalable deployments. We describe the architecture, provide workflows for the end-to-end management of AI-based applications, and show the viability of the architecture through multiple use cases.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
6G, AI-Native Networks, E2E network management, Reusable AI-based applications
host publication
Proceedings of the 14th International Conference on Network of the Future, NoF 2023
series title
Proceedings of the 14th International Conference on Network of the Future, NoF 2023
editor
Chemouil, Prosper ; Sayit, Muge ; Fu, Xiaoming ; Naboulsi, Diala ; Cetinkaya, Cihat and Stanica, Razvan
pages
5 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
14th International Conference on Network of the Future, NoF 2023
conference location
Izmir, Turkey
conference dates
2023-10-04 - 2023-10-06
external identifiers
  • scopus:85178518196
ISBN
9798350338072
DOI
10.1109/NoF58724.2023.10302791
language
English
LU publication?
yes
id
8669ed38-3384-4e04-9fac-6dfb75080914
date added to LUP
2024-01-04 14:11:40
date last changed
2024-01-04 14:12:14
@inproceedings{8669ed38-3384-4e04-9fac-6dfb75080914,
  abstract     = {{<p>Artificial intelligence (AI) is a key enabler for future 6G networks. Currently, related architecture works propose AI-based applications and network services that are dedicated to specific tasks (e.g., improving the performance of RAN with AI). These proposed architectures offer a unique way to collect data, process it, and extract features from data for each AI-based application. However, this dedicated approach creates AI-silos that hinder the integration of AI in the networks. In other words, such AI-silos create a set of AI-models and data for AI-based applications that only work within a single dedicated task. This single-task approach limits the end-to-end integration of AI in the networks. In this work, we propose a network architecture to deploy AI-based applications, at different network domains, that prevents AI-silos by offering reusable data and models to ensure scalable deployments. We describe the architecture, provide workflows for the end-to-end management of AI-based applications, and show the viability of the architecture through multiple use cases.</p>}},
  author       = {{Brito, Flavio and Cisneros, Josue Castaneda and Linder, Neiva and Riggio, Roberto and Coronado, Estefania and Palomares, Javier and Adzic, Jovanka and Renart, Javier and Lindgren, Anders and Rosa, Miguel and Odling, Per}},
  booktitle    = {{Proceedings of the 14th International Conference on Network of the Future, NoF 2023}},
  editor       = {{Chemouil, Prosper and Sayit, Muge and Fu, Xiaoming and Naboulsi, Diala and Cetinkaya, Cihat and Stanica, Razvan}},
  isbn         = {{9798350338072}},
  keywords     = {{6G; AI-Native Networks; E2E network management; Reusable AI-based applications}},
  language     = {{eng}},
  pages        = {{98--102}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{Proceedings of the 14th International Conference on Network of the Future, NoF 2023}},
  title        = {{A network architecture for scalable end-to-end management of reusable AI-based applications}},
  url          = {{http://dx.doi.org/10.1109/NoF58724.2023.10302791}},
  doi          = {{10.1109/NoF58724.2023.10302791}},
  year         = {{2023}},
}