Computation-aware Energy-harvesting Federated Learning: Cyclic Scheduling with Selective Participation

2025-11-14

AI Summary

In energy-harvesting federated learning (EHFL), client participation is unstable and computationally energy-intensive due to battery constraints. Method: This paper proposes FedBacys, a battery-aware cyclic scheduling framework, and its lightweight variant FedBacys-Odd. Its core innovation lies in the first integration of battery-state-driven periodic participation with clustering-guided selective client selection—reducing redundant computation while preserving model convergence. Contribution/Results: Theoretical analysis establishes convergence guarantees. Experiments demonstrate that, compared to state-of-the-art baselines, FedBacys achieves comparable model accuracy and convergence speed while reducing system energy consumption by 32.7%, significantly improving device participation robustness and energy utilization efficiency.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Federated Learning (FL) is a powerful paradigm for distributed learning, but its increasing complexity leads to significant energy consumption from client-side computations for training models. In particular, the challenge is critical in energy-harvesting FL (EHFL) systems where participation availability of each device oscillates due to limited energy. To address this, we propose FedBacys, a battery-aware EHFL framework using cyclic client participation based on users' battery levels. By clustering clients and scheduling them sequentially, FedBacys minimizes redundant computations, reduces system-wide energy usage, and improves learning stability. We also introduce FedBacys-Odd, a more energy-efficient variant that allows clients to participate selectively, further reducing energy costs without compromising performance. We provide a convergence analysis for our framework and demonstrate its superior energy efficiency and robustness compared to existing algorithms through numerical experiments.

Problem

• Optimizes energy consumption in federated learning with energy-harvesting clients
• Manages fluctuating device participation due to limited battery levels
• Reduces redundant computations while maintaining learning performance stability

Innovation

• Cyclic client participation scheduling based on battery levels
• Clustering clients to minimize redundant computations
• Selective participation variant for enhanced energy efficiency