FLEAT: Energy-Accuracy Trade-off in Federated Learning over Heterogeneous Edge Devices

Abstract

Federated Learning (FL) enables collaborative model training across edge devices but faces challenges balancing energy consumption, heterogeneous resources, and accuracy in IoT ecosystems. Existing solutions often overlook adaptive coordination of computation and communication or depend on hardware-level adjustments unavailable on constrained devices. We propose FLEAT (Federated Learning Energy and Accuracy Tuning), a framework that jointly optimizes energy efficiency and model accuracy via dynamic local update adaptation and gradient-informed layer-wise pruning. FLEAT introduces a theoretical error bound for synchronous FL under these mechanisms and employs an energy-aware optimization loop to allocate per-device computation/communication time. By scaling local updates to device capabilities and pruning redundant layers based on parameter importance, FLEAT mitigates stragglers, reduces communication overhead, and stabilizes convergence via normalized gradient aggregation. We evaluate FLEAT in both real-world IoT deployments and simulated edge networks. At a fixed wall-clock budget, FLEAT achieves a higher convergence rate-reaching higher accuracy earlier-than FedAvg, FedProx, and FedNova; when all methods train to completion, it remains within 1.2-3.1% of FedAvg's final accuracy while cutting total energy by 16.2%. Relative to existing studies, FLEAT matches or surpasses their accuracy while strictly lowering energy, owing to its joint tuning of local steps and pruning under an energyaware objective. This work bridges model- and system-level optimizations, offering a scalable solution for energy-accuracy equilibrium in heterogeneous FL deployments.