When and how to update AI/ML models in 6G resource-constrained network domains?
(2024) 2024 Joint European Conference on Networks and Communications and 6G Summit, EuCNC/6G Summit 2024 p.937-942- Abstract
Artificial intelligence and Machine Learning (AI/ML) are steadily becoming widespread across all layers in the current mobile network generation. The next generation of networks, namely 6G, will consider AI/ML as a foundational block to deliver all expected results of such networks. Thus, the management of AI/ML applications across different layers of 6G is paramount for the success of the next generation of mobile networks. However, current approaches to the management of AI/ML, namely Machine Learning Operations (MLOps), focus mostly on independent AI/ML operations for a specific problem with the goal of improving the performance of the overall models of the AI/ML application. While this approach is useful for scenarios where... (More)
Artificial intelligence and Machine Learning (AI/ML) are steadily becoming widespread across all layers in the current mobile network generation. The next generation of networks, namely 6G, will consider AI/ML as a foundational block to deliver all expected results of such networks. Thus, the management of AI/ML applications across different layers of 6G is paramount for the success of the next generation of mobile networks. However, current approaches to the management of AI/ML, namely Machine Learning Operations (MLOps), focus mostly on independent AI/ML operations for a specific problem with the goal of improving the performance of the overall models of the AI/ML application. While this approach is useful for scenarios where resources are plentiful, such as the cloud layer, in resource-constrained network domains, focusing only on performance is not the best approach. For example, in the network edge domain, resources such as energy and computation are limited; thus, when and how to update an AI/ML model is a critical question to answer. In this paper, we focus on MLOps in scenarios with limited resources. To this end, we propose a network component for 6G, namely the Model Manager. This component automatically decides when and how to update a given AI/ML model based on both performance and resource consumption points of view. For this, we introduce a Model Manager model score to decide the approach to updating an AI/ML model. Our experiments show that by using this score, the model manager could find suitable situations on how to update a model without manual configuration.
(Less)
- author
- Brito, Flavio ; Cisneros, Josue Castaneda ; Ghebretensae, Zere ; Linder, Neiva LU and Odling, Per LU
- organization
- publishing date
- 2024
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- 6G, AI/ML, MLOps, Mobile Networks
- host publication
- 2024 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)
- pages
- 6 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2024 Joint European Conference on Networks and Communications and 6G Summit, EuCNC/6G Summit 2024
- conference location
- Antwerp, Belgium
- conference dates
- 2024-06-03 - 2024-06-06
- external identifiers
-
- scopus:85199885674
- ISBN
- 9798350344998
- DOI
- 10.1109/EuCNC/6GSummit60053.2024.10597011
- language
- English
- LU publication?
- yes
- id
- 7672a40e-e76b-4fbc-834d-912af5042b12
- date added to LUP
- 2024-11-11 15:39:21
- date last changed
- 2025-04-04 14:51:20
@inproceedings{7672a40e-e76b-4fbc-834d-912af5042b12, abstract = {{<p>Artificial intelligence and Machine Learning (AI/ML) are steadily becoming widespread across all layers in the current mobile network generation. The next generation of networks, namely 6G, will consider AI/ML as a foundational block to deliver all expected results of such networks. Thus, the management of AI/ML applications across different layers of 6G is paramount for the success of the next generation of mobile networks. However, current approaches to the management of AI/ML, namely Machine Learning Operations (MLOps), focus mostly on independent AI/ML operations for a specific problem with the goal of improving the performance of the overall models of the AI/ML application. While this approach is useful for scenarios where resources are plentiful, such as the cloud layer, in resource-constrained network domains, focusing only on performance is not the best approach. For example, in the network edge domain, resources such as energy and computation are limited; thus, when and how to update an AI/ML model is a critical question to answer. In this paper, we focus on MLOps in scenarios with limited resources. To this end, we propose a network component for 6G, namely the Model Manager. This component automatically decides when and how to update a given AI/ML model based on both performance and resource consumption points of view. For this, we introduce a Model Manager model score to decide the approach to updating an AI/ML model. Our experiments show that by using this score, the model manager could find suitable situations on how to update a model without manual configuration.</p>}}, author = {{Brito, Flavio and Cisneros, Josue Castaneda and Ghebretensae, Zere and Linder, Neiva and Odling, Per}}, booktitle = {{2024 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)}}, isbn = {{9798350344998}}, keywords = {{6G; AI/ML; MLOps; Mobile Networks}}, language = {{eng}}, pages = {{937--942}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{When and how to update AI/ML models in 6G resource-constrained network domains?}}, url = {{http://dx.doi.org/10.1109/EuCNC/6GSummit60053.2024.10597011}}, doi = {{10.1109/EuCNC/6GSummit60053.2024.10597011}}, year = {{2024}}, }