用轻量级模型实现在微控制器上实时识别家电用电状态。
A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUs
- 将用电监测转为分类任务，用极限机器实现低功耗推理。
- 在REDD数据集上四设备识别准确率80%，延迟仅0.43毫秒。
- 模型仅占17KB内存，适合隐私敏感的本地部署场景。
非侵入式负载监测（NILM）系统通过单一总电表估算各电器能耗，无需为每个设备安装独立传感器。传统方法依赖计算量大的优化算法处理离线数据，难以在资源受限的设备上实时运行，且存在隐私风险。本文提出基于极限机器（Tsetlin Machine）的NILM框架，专为嵌入式微控制器设计，支持本地化隐私保护部署。将问题重构为分类任务，在REDD数据集上实现两设备分类平均精度90%、召回率96%，四设备分类精度77%、召回率80%。模型仅占用17KB闪存空间，在ESP32上推理延迟为0.43毫秒，验证了其在微控制器上的适用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。