Search papers, labs, and topics across Lattice.
This paper introduces a Tsetlin Machine-based Non-Intrusive Load Monitoring (NILM) framework designed for real-time applications on resource-constrained microcontrollers (MCUs). By reformulating the NILM problem as a classification task, the proposed system achieves impressive performance metrics, including 90% precision and 96% recall for two-appliance classification, while maintaining a minimal memory footprint of 18 KB and low inference latency of 0.43 ms. This advancement enables effective and privacy-preserving energy monitoring in embedded systems, addressing the limitations of traditional computationally intensive NILM approaches.
Achieving 90% precision in real-time energy monitoring on microcontrollers could revolutionize how we deploy NILM systems in privacy-sensitive environments.
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 18 KB of flash memory and achieves an inference latency of 0.43 ms on an ESP32, demonstrating its suitability for embedded NILM applications on MCUs.
