A Lightweight Emulation Framework for Energy-Aware Federated Learning
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.
Authors
- Ramon dos Reis Fontes (ORCID: https://orcid.org/0000-0003-0012-4284)
- Vinícius F. S. Mota (ORCID: https://orcid.org/0000-0002-8341-8183)
- Rodolfo da Silva Villaça (ORCID: https://orcid.org/0000-0002-8051-3978)
- Eduardo Cerqueira (ORCID: https://orcid.org/0000-0003-2162-6523)
- Johann J. Schmitz Bastos (ORCID: https://orcid.org/0000-0002-2763-7162)
- J. Batista (ORCID: https://orcid.org/0009-0006-8300-8236)
Institutions
- Universidade Federal do Rio Grande do Norte (BR)
- Universidade Federal do Espírito Santo (BR)
- Universidade Federal do Pará (BR)
Publication Details
- Published
- 2025-09-08
- DOI
- https://doi.org/10.1145/3744969.3748395
- Primary Topic
- Software-Defined Networks and 5G
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação de Amparo à Pesquisa e Inovação do Espírito Santo