这篇论文教你怎么在能耗不稳定的MCU上做持续学习，不用反复上机测试，Cortex-M4上误差只有16.6%。
该研究提出一种为微控制器单元（MCU）设计深度神经网络（DNN）的方法，适用于太阳能供电等能量可能中断的间歇性设备。方法结合硬件感知能量预测模型与多目标优化（MOO），在离线设计阶段完成DNN优化，无需在目标MCU上反复部署测试。能量预测器基于DNN的算力和存储特征，估算推理、训练及间歇检查点开销的逐层能耗。在Cortex-M4 MCU上用自编码器进行异常检测验证，预测器的加权绝对百分比误差为16.6%，足以在中断约束下可靠选择架构。
Design-Time Optimization of Deep Neural Networks for Intermittent Learning on Microcontrollers
We present a method for designing deep neural networks (DNNs) for intermittent, energy-autonomous, on-device learning on microcontroller units (MCUs). In mobile applications where the energy can run out, e.g., when solar-powered, executing artificial intelligence (AI) faces a technical issue as learning can be interrupted at any time. Our approach combines a hardware-aware energy prediction model with multi-objective optimization (MOO), enabling offline DNN optimization at the design stage without repeated deployment and online testing on the target MCU. Our proposed energy predictor estimates per-layer energy consumption for both DNN inference and training, including the intermittent checkpointing overhead, based on implementation-specific compute and memory features extracted from the DNN model. We validate our approach using autoencoders for anomaly detection on a Cortex-M4 MCU, where our predictor achieves a weighted absolute percentage error of 16.6%, which is sufficient for reliable architecture selection under intermittency constraints. As a result, this work bridges the gap between MOO, automated DNN design, deployment on energy-harvesting systems, and intermittent learning, truly enabling autonomous AI at the edge.