Deep learning (DL) models have emerged as a promising solution for Internet of Things (IoT) applications. However, due to their computational complexity, DL models consume significant amounts of energy, which can rapidly drain the battery and compromise the performance of IoT devices. For sustainable operation, we consider an edge device with a rechargeable battery and energy harvesting (EH) capabilities. In addition to the stochastic nature of the ambient energy source, the harvesting rate is often insufficient to meet the inference energy requirements, leading to drastic performance degradation in energy-agnostic devices. To mitigate this problem, we propose energy-adaptive dynamic early exiting (EE) to enable efficient and accurate inference in an EH edge intelligence system. Our approach derives an energy-aware EE policy that determines the optimal amount of computational processing on a per-sample basis. The proposed policy balances the energy consumption to match the limited incoming energy and achieves continuous availability. Numerical results show that accuracy and service rate are improved up to 25% and 35%, respectively, in comparison with an energy-agnostic policy.

翻译：深度学习（DL）模型已成为物联网（IoT）应用中的一种有前景的解决方案。然而，由于其计算复杂度，深度学习模型会消耗大量能量，从而迅速耗尽电池并损害物联网设备的性能。为实现可持续运行，我们考虑一种配备可充电电池和能量收集（EH）能力的边缘设备。除了环境能源的随机性外，能量收集率通常不足以满足推理所需的能量，导致能量不可知设备性能严重下降。为缓解此问题，我们提出能量自适应动态提前退出（EE）机制，以实现能效边缘智能系统中的高效准确推理。我们的方法推导出一种能量感知的EE策略，该策略基于每个样本确定最优计算处理量。所提出的策略平衡能量消耗以适应有限的输入能量，并实现持续可用性。数值结果表明，与能量不可知策略相比，准确度和服务率分别提高了25%和35%。