Feature-Based Semantics-Aware Scheduling for Energy-Harvesting Federated Learning

2025-12-01

AI Summary

In energy-constrained edge environments, local training energy consumption in federated learning (FL) often dominates communication overhead; yet existing energy-harvesting FL (EHFL) scheduling strategies neglect computational redundancy, leading to suboptimal energy efficiency. Method: We propose a semantic-aware lightweight client scheduling framework that innovatively integrates version age of information (VAoI) with intermediate-layer features of deep neural networks (DNNs) to construct a feature-based surrogate model—enabling single-forward estimation of both update timeliness and semantic importance, thereby avoiding the high computational complexity of conventional VAoI, which operates in the full-parameter space. Contribution/Results: Our approach enables low-overhead, semantics-driven proactive resource management. Experiments under extreme non-IID data distributions and severe energy scarcity demonstrate significant reductions in energy consumption and accelerated model convergence, outperforming state-of-the-art baselines.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Federated Learning (FL) on resource-constrained edge devices faces a critical challenge: The computational energy required for training Deep Neural Networks (DNNs) often dominates communication costs. However, most existing Energy-Harvesting FL (EHFL) strategies fail to account for this reality, resulting in wasted energy due to redundant local computations. For efficient and proactive resource management, algorithms that predict local update contributions must be devised. We propose a lightweight client scheduling framework using the Version Age of Information (VAoI), a semantics-aware metric that quantifies update timeliness and significance. Crucially, we overcome VAoI's typical prohibitive computational cost, which requires statistical distance over the entire parameter space, by introducing a feature-based proxy. This proxy estimates model redundancy using intermediate-layer extraction from a single forward pass, dramatically reducing computational complexity. Experiments conducted under extreme non-IID data distributions and scarce energy availability demonstrate superior learning performance while achieving energy reduction compared to existing baseline selection policies. Our framework establishes semantics-aware scheduling as a practical and vital solution for EHFL in realistic scenarios where training costs dominate transmission costs.

Problem

• Scheduling energy-harvesting federated learning to reduce computational energy waste
• Overcoming high computational cost of semantics-aware metrics for efficient scheduling
• Improving learning performance under non-IID data and scarce energy conditions

Innovation

• Feature-based proxy reduces VAoI computational cost
• Semantics-aware scheduling uses Version Age of Information
• Lightweight framework optimizes energy in federated learning