AI 中文总结
本文提出基于Tsetlin机的NILM框架，解决传统NILM难在MCU部署的问题，在REDD数据集上实现高分类精度，模型体积小、推理延迟低，适配MCU嵌入式应用。
AI 中文摘要
非侵入式负荷监测（NILM）系统可通过单个总电表估算各电器能耗，无需为每个设备单独安装传感器，仅需在建筑内安装一块测量总用电量的电表，就能确定各电器的工作状态。但传统NILM系统采用计算密集型优化算法处理离线数据，限制了其在需本地处理敏感家庭数据的设备端部署能力。本文提出一种基于Tsetlin机（TM）的NILM框架，针对资源受限的微控制器（MCU）实时应用，实现隐私保护的边缘部署。该问题被重新表述为分类任务，在REDD数据集上，所提方法对两台电器分类的平均精度为90%、召回率为96%，对四台电器分类的精度为77%、召回率为80%；训练后的模型仅占用18KB闪存，在ESP32上的推理延迟为0.43ms，证明其适用于MCU上的嵌入式NILM应用。
英文摘要
Non-Intrusive Load Monitoring (NILM) systems estimate individual appliance energy consumption from a single aggregate meter, without requiring separate sensors for each device. By installing a single meter that measures a building's total electricity consumption, NILM algorithms can determine the active status of each appliance. However, traditional NILM systems use computationally intensive optimization algorithms to process offline data, limiting their capability for on-device deployment, where sensitive household data must be processed locally. This paper proposes a Tsetlin Machine (TM)-based NILM framework, targeting real-time applications on resource-constrained microcontrollers (MCUs), enabling privacy-preserving edge deployment. The problem is reformulated as a classification task, and the proposed approach achieves an average precision of 90% and recall of 96% for two-appliance classification, and 77% precision and 80% recall for four appliances on the REDD dataset. The trained model occupies only 17 KB of flash memory and achieves an inference latency of 0.43 ms on an ESP32, demonstrating its suitability for NILM applications on MCUs.
CommentsAccepted by International Symposium on the Tsetlin Machine (ISTM 2026)
