Energy-Efficient Federated Learning for AIoT Using Clustering Methods
While substantial research has been devoted to optimizing model performance, convergence rates, and communication efficiency, the energy implications of federated learning (FL) within Artificial Intelligence of Things (AIoT) scenarios are often overlooked in the existing literature. This study exami...
| Authors: | , , , |
|---|---|
| Format: | article |
| Status: | Published version |
| Publication Date: | 2025 |
| Country: | España |
| Institution: | Centre Tecnològic de Telecomunicacions de Catalunya (CTTC) |
| Repository: | r-CTTC. Repositorio Institucional Producción Científica del Centre Tecnològic de Telecomunicacions de Catalunya (CTTC) |
| OAI Identifier: | oai:cttc.fundanetsuite.com:p8699 |
| Online Access: | https://cttc.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=8699 |
| Access Level: | Open access |
| Keyword: | Training Internet of Things Artificial intelligence Convergence Data models Servers Computational modeling Costs Distributed databases Energy consumption Artificial Intelligence of Things (AIoT) device selection clustering energy efficiency federated learning (FL) |
| Summary: | While substantial research has been devoted to optimizing model performance, convergence rates, and communication efficiency, the energy implications of federated learning (FL) within Artificial Intelligence of Things (AIoT) scenarios are often overlooked in the existing literature. This study examines the energy consumed during the FL process, focusing on three main energy-intensive processes: 1) preprocessing; 2) communication; and 3) local learning, all contributing to the overall energy footprint. We rely on the observation that device/client selection is crucial for speeding up the convergence of model training in a distributed AIoT setting and propose two clustering-informed methods. These clustering solutions are designed to group AIoT devices with similar label distributions, resulting in clusters composed of nearly heterogeneous devices. Hence, our methods alleviate the heterogeneity often encountered in real-world distributed learning applications. Throughout extensive numerical experimentation, we demonstrate that our clustering strategies typically achieve high convergence rates while maintaining low energy consumption when compared to other recent approaches available in the literature. |
|---|