EH-FedSAG: Variance-Reduced Federated Learning with Energy-Aware Participation in Energy-Harvesting IoT

Federated learning (FL) in energy-harvesting (EH) networks is challenged by intermittent and stochastic energy arrivals that lead to unstable device participation across training rounds, and by high communication costs under limited energy budgets, reducing overall training efficiency. This paper studies FL under a slot-based EH model and proposes EH-FedSAG, a server-memory-based variance-reduced method. We compare EH-FedSAG with vanilla EH-FedAvg under the same multi-channel orthogonal multiple-access uplink model and within a unified simulation framework that captures battery charging, local computation cost, and transmission cost under different energy-arrival probabilities. Performance is assessed in terms of test accuracy over training rounds for both homogeneous and heterogeneous data distributions. The results show that EH-FedSAG consistently achieves higher test accuracy than EH-FedAvg in the considered settings, while exhibiting substantially lower training variance. The advantage of EH-FedSAG is more pronounced under scarce energy availability and non-independent/identically-distributed data.

Energy-Aware Multi-Exit TinyML for Smart Zero-Energy Devices

The proliferation of smart and autonomous systems has motivated a shift toward executing intelligence directly on edge devices. This shift becomes particularly challenging for zero-energy devices (ZEDs), where severe constraints on memory, energy availability, and inference accuracy must be addressed simultaneously. In this paper, we present a unified approach to managing these constraints for smart ZEDs. Specifically, we design, train, and deploy a tiny machine learning (TinyML) model for person detection on a ZED. The proposed architecture stores a single model in memory while enabling adaptive inference through multiple exit points, allowing computational effort to scale with input difficulty. As a result, low-energy inference is performed for easy instances, while higher-precision inference is selectively employed for harder cases. This strategy significantly reduces energy consumption without sacrificing detection accuracy. Furthermore, to enhance device autonomy and prevent power failures, we introduce auxiliary energy-aware circuits that dynamically regulate system operation based on available energy. Compared with a state-of-the-art energy-aware single-exit TinyML approach, the proposed method achieves an energy consumption reduction of approximately $29.6\%$. Overall, the proposed framework is appealing for enabling accurate and energy-efficient intelligence on ZED platforms.

Evaluating Task Execution Performance Under Energy Measurement Overhead

Energy-awareness for adapting task execution behavior can bring several benefits in terms of performance improvement in energy harvesting (EH) Internet of Things (IoT) devices. However, the energy measurement cost of acquiring energy information, which is traditionally ignored, can potentially neutralize or even reverse the potential benefits. This paper highlights operational parameters, such as energy measurement frequency and task execution frequency, which can be tuned to improve the task execution performance of an EH-IoT device. To this end, we consider energy-blind (EB) and energy-aware (EA) task decision approaches and compare their task completion rate performance. We show that, for specific hardware design parameters of an EH-IoT device, there exists an optimal energy measurement/task execution frequency that can maximize the task completion rate in both approaches. Moreover, if these parameters are not chosen appropriately, then energy measurement costs can cause EA scheduling to underperform compared to EB scheduling.