Trimming Feature Extraction and Inference for MCU-Based Edge NILM: A Systematic Approach

Nonintrusive load monitoring (NILM) enables the disaggregation of the global power consumption of multiple loads, taken from a single smart electrical meter, into appliance-level details. State-of-the-art approaches are based on machine learning methods and exploit the fusion of time- and frequency-...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on industrial informatics Jg. 18; H. 2; S. 943 - 952
Hauptverfasser: Tabanelli, Enrico, Brunelli, Davide, Acquaviva, Andrea, Benini, Luca
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.02.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Cost reduction
Edge processing
Electric potential
Electricity meters
Feature extraction
Hardware
Home appliances
low-power microcontroller units (MCUs)
Machine learning
machine learning (ML)
Meters
Microcontrollers
nonintrusive load monitoring (NILM)
Optimization
Performance evaluation
Power consumption
Real-time systems
Sensors
Voltage
Voltage measurement
ISSN:1551-3203, 1941-0050
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Nonintrusive load monitoring (NILM) enables the disaggregation of the global power consumption of multiple loads, taken from a single smart electrical meter, into appliance-level details. State-of-the-art approaches are based on machine learning methods and exploit the fusion of time- and frequency-domain features from current and voltage sensors. Unfortunately, these methods are compute-demanding and memory-intensive. Therefore, running low-latency NILM on low-cost resource-constrained microcontroller unit (MCU)-based meters is currently an open challenge. This article addresses the optimization of the feature spaces as well as the computational and storage cost reduction needed for executing state-of-the-art (SoA) NILM algorithms on memory- and compute-limited MCUs. We compare four supervised learning techniques on different classification scenarios and characterize the overall NILM pipeline's implementation on an MCU-based Smart Measurement Node . Experimental results demonstrate that optimizing the feature space enables edge MCU-based NILM with 95.15% accuracy, resulting in a small drop compared to the most accurate feature vector deployment (96.19%) while achieving up to 5.45× speedup and 80.56% storage reduction. Furthermore, we show that low-latency NILM relying only on current measurements reaches almost 80% accuracy, allowing a major cost reduction by removing voltage sensors from the hardware (HW) design.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2021.3078186