Energy-Efficient Federated Learning for AIoT using Clustering Methods

2025-05-14

AI Summary

In AIoT-enabled federated learning (FL), high energy consumption in preprocessing, communication, and local training—coupled with the neglect of system-level energy efficiency optimization in existing work—poses critical challenges. To address this, we propose a label-distribution-aware device clustering method that, for the first time, incorporates label distribution similarity into client selection to form approximately homogeneous device clusters, thereby jointly mitigating data heterogeneity and reducing energy consumption. Our approach integrates K-means and spectral clustering for similarity measurement, and couples it with a heterogeneity-aware and energy-aware training framework. Experiments demonstrate that, compared to state-of-the-art baselines, our method improves convergence speed by 23%–37% and reduces total edge-side energy consumption by 41%–58%, achieving significant gains in both efficiency and energy efficiency.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

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: pre-processing, communication, and 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.

Problem

• Optimize energy use in federated learning for AIoT
• Address device heterogeneity in distributed learning applications
• Improve convergence rates while reducing energy consumption

Innovation

• Clustering methods group similar AIoT devices
• Reduces energy in pre-processing and communication
• Improves convergence rates with low energy