| Texto completo | |
| Autor(es): |
Bastos, Johann
;
Batista, Joao
;
Fontes, Ramon
;
Cerqueira, Eduardo
;
Villaca, Rodolfo
;
Mota, Vinicius F. S.
Número total de Autores: 6
|
| Tipo de documento: | Artigo Científico |
| Fonte: | PROCEEDINGS OF THE 2025 ACM SIGCOMM 2025 POSTERS AND DEMOS, SIGCOMM 2025; v. N/A, p. 2-pg., 2025-01-01. |
| Resumo | |
IoT networks face critical challenges in energy efficiency, privacy, and communication reliability. Federated Learning (FL) enables collaborative model training without sharing raw data, but traditional client selection can drain energy and disrupt RPL-based networks. This demo introduces MininetFed, a network emulator with FL support in an energy-aware client selection strategy. Clients are chosen based on energy availability, balancing model accuracy and network longevity. Users can interact with different topologies and selection algorithms, with results showing enhanced learning efficiency and extended network lifetime in multi-hop IoT scenarios. (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 |