Battery-aware Cyclic Scheduling in Energy-harvesting Federated Learning

2025-04-16

AI Summary

To address unstable client participation, high computational redundancy, and low energy efficiency in energy-harvesting federated learning (EHFL) caused by battery-level fluctuations, this paper proposes FedBacys—a battery-aware cyclic scheduling framework. Methodologically, it introduces, for the first time in EHFL, a battery-state-driven cyclic participation mechanism that jointly optimizes client clustering, temporally ordered local training, and periodic participation control under resource constraints, while unifying communication and computation cost modeling. The framework ensures robustness under both non-IID data distributions and extremely low energy-harvesting frequencies. Experiments demonstrate that, under sparse charging and non-IID conditions, FedBacys reduces model accuracy variance by 37%, improves system energy efficiency by 2.1×, and significantly enhances convergence stability and energy savings.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Reasoning under Uncertainty: Stochastic Optimization

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
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Federated Learning (FL) has emerged as a promising framework for distributed learning, but its growing complexity has led to significant energy consumption, particularly from computations on the client side. This challenge is especially critical in energy-harvesting FL (EHFL) systems, where device availability fluctuates due to limited and time-varying energy resources. We propose FedBacys, a battery-aware FL framework that introduces cyclic client participation based on users' battery levels to cope with these issues. FedBacys enables clients to save energy and strategically perform local training just before their designated transmission time by clustering clients and scheduling their involvement sequentially. This design minimizes redundant computation, reduces system-wide energy usage, and improves learning stability. Our experiments demonstrate that FedBacys outperforms existing approaches in terms of energy efficiency and performance consistency, exhibiting robustness even under non-i.i.d. training data distributions and with very infrequent battery charging. This work presents the first comprehensive evaluation of cyclic client participation in EHFL, incorporating both communication and computation costs into a unified, resource-aware scheduling strategy.

Problem

• Reduces energy consumption in energy-harvesting Federated Learning systems
• Manages fluctuating device availability due to varying battery levels
• Optimizes client participation scheduling to minimize redundant computations

Innovation

• Battery-aware cyclic client participation scheduling
• Energy-efficient clustering and sequential training
• Unified resource-aware communication and computation strategy