Federated Learning-based Adaptive Idle-Time Training for Energy-Efficient Edge Nodes
Document Type
Conference Proceeding
Source of Publication
Digest of Technical Papers IEEE International Conference on Consumer Electronics
Publication Date
2-3-2026
Abstract
Federated Learning (FL) enables collaborative model training across distributed edge devices without sharing raw data, yet its deployment in energy-constrained IoT environments remains inefficient. This paper proposes Fed-Idle, an Adaptive Idle-Time Training framework that improves energy efficiency by aligning local computation with each device's power and workload context. Each node monitors its battery, CPU utilization, and charging state, activating training only during idle or charging periods. A centralized coordinator aggregates updates from active nodes using staleness-aware weighting. Experiments on the CIFAR-10 dataset show that Fed-Idle achieves up to 40% lower energy consumption, 25% faster convergence, and a 5% reduction in client dropout, while maintaining comparable accuracy to FedAvg and FedProx. These results demonstrate that idle-time-aware scheduling provides an effective foundation for sustainable federated edge intelligence.
DOI Link
ISBN
[9798331553432]
ISSN
Publisher
IEEE
Disciplines
Computer Sciences
Keywords
Adaptive scheduling, Edge computing, Energy efficiency, Federated learning, Internet of Things (IoT)
Scopus ID
Recommended Citation
Asad, Muhammad and Otoum, Safa, "Federated Learning-based Adaptive Idle-Time Training for Energy-Efficient Edge Nodes" (2026). All Works. 8188.
https://zuscholars.zu.ac.ae/works/8188
Indexed in Scopus
yes
Open Access
no