This paper addresses the problem of efficient federated learning in energy-harvesting AIoT systems, where time-varying energy availability may lead to device blackouts and unstable learning performance. To address this issue, we propose an energy-adaptive multi-dimensional learning control framework that jointly determines model complexity and training intensity based on the real-time energy state of each device. This method integrates multiple control dimensions, including model pruning, quantization, knowledge distillation, and adaptive local training, into a unified decision mechanism under an energy constraint. Each device determines its participation in federated learning based on its residual energy relative to an energy threshold. When participating, the device selects a feasible learning configuration that jointly considers training intensity (e.g., epoch size and batch size) and lightweight learning operations to maximize learning effectiveness while preventing energy depletion. The proposed framework was implemented on a real-world testbed using NVIDIA Jetson Orin Nano devices under solar-energy-harvesting conditions. Our experimental results demonstrate that the proposed method significantly reduces device blackout while maintaining competitive model accuracy with respect to energy-unconstrained scenarios. These results highlight that joint control of multiple learning-cost factors is essential for achieving stable and efficient federated learning in energy-harvesting AIoT environments.
Noh et al. (Tue,) studied this question.