| Texto completo | |
| Autor(es): |
Xavier, Bruno Missi
;
Silva Guimaraes, Rafael
;
Comarela, Giovanni
;
Martinello, Magnos
Número total de Autores: 4
|
| Tipo de documento: | Artigo Científico |
| Fonte: | IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT; v. 19, n. 4, p. 13-pg., 2022-12-01. |
| Resumo | |
Self-driving networks guided by machine-learning (ML) algorithms are the driving force for building networks of the future. ML is effective at making inferences about data that is too complex or too unpredictable for humans. The network softwarization enabled by a deep programmability approach opens up new opportunities to deploy ML at the programmable data plane. In this paper, we introduce the MAP4 as a framework that explores the feasibility of mapping ML models in programmable network devices. To achieve this, we rely on the P4 language to deploy a pre-trained model into a programmable switch, utilizing the ML model to accurately classify flows at line rate. Our approach demonstrates that ML models working as classifiers can better fit the data by using the new levels of network programmability from the P4 language. The results showed that with few packets, most of the flows are properly classified. In some use cases, with two packets in the flow, 97% of traffic can be correctly classified, and all classes are properly labeled with a maximum of four packets. (AU) | |
| Processo FAPESP: | 20/05182-3 - PORVIR-5G: programabilidade, orquestração e virtualização em redes 5G |
| Beneficiário: | José Marcos Silva Nogueira |
| Modalidade de apoio: | Auxílio à Pesquisa - Temático |
| Processo FAPESP: | 20/05174-0 - SAWI - Savvy Access through Worldwide Internet |
| Beneficiário: | Epaminondas Aguiar de Sousa Junior |
| Modalidade de apoio: | Auxílio à Pesquisa - Pesquisa Inovativa em Pequenas Empresas - PIPE |
| Processo FAPESP: | 18/23097-3 - SFI2: fatiamento de infraestruturas de internet do futuro |
| Beneficiário: | Tereza Cristina Melo de Brito Carvalho |
| Modalidade de apoio: | Auxílio à Pesquisa - Temático |