Exploiting Smart Meter Power Consumption Measurements for Human Activity Recognition (HAR) with a Motif-Detection-Based Non-Intrusive Load Monitoring (NILM) Approach

Abstract

Numerous approaches exist for disaggregating power consumption data, referred to as non-intrusive load monitoring (NILM). Whereas NILM is primarily used for energy monitoring, we intend to disaggregate a household’s power consumption to detect human activity in the residence. Therefore, this paper presents a novel approach for NILM, which uses pattern recognition on the raw power waveform of the smart meter measurements to recognize individual household appliance actions. The presented NILM approach is capable of (near) real-time appliance action detection in a streaming setting, using edge computing. It is unique in our approach that we quantify the disaggregating uncertainty using continuous pattern correlation instead of binary device activity states. Further, we outline using the disaggregated appliance activity data for human activity recognition (HAR). To evaluate our approach, we use a dataset collected from actual households. We show that the developed NILM approach works, and the disaggregation quality depends on the pattern selection and the appliance type. In summary, we demonstrate that it is possible to detect human activity within the residence using a motif-detection-based NILM approach applied to smart meter measurements.

Electricity Theft Detection for Smart Homes: Harnessing the Power of Machine Learning With Real and Synthetic Attacks

“…Table 1 shows some available literature on appliance consumption, however, there is a significant gap in knowledge regarding the utilization of appliance consumption patterns to train a classifier for electricity theft detection in smart homes. Although there is extensive research on appliance consumption patterns [25], [14], [15], there is a lack of specific focus on using these patterns to train a classifier for electricity theft detection. Existing literature primarily discusses load disaggregation, human activity recognition, and energy consumption forecasting based on appliance power consumption patterns.…”

“…Additionally, some studies discuss the application of appliance power consumption patterns for simulating human living activities [15] and improving residential load disaggregation [11]. Furthermore, some studies have emphasized the accuracy of identifying appliance usage patterns using the proposed models [25], [14].…”

Multi-Agent Systems for Resource Allocation and Scheduling in a Smart Grid

“…The authors stated in [ 180 ], that the sensor measurements are used only in software-based (smart meter) methods. Because it requires only one detection site, NILM offers a low-cost approach.…”

Diseño e Implementación de un Medidor Trifásico Inteligente de Energía Eléctrica y Armónicos

“…La visibilidad del consumo de energía se ha convertido en una herramienta poderosa para los usuarios residenciales, haciendo posible un mayor control sobre el uso de sus electrodomésticos y otras cargas [12]. Esta capacidad de observar el consumo en tiempo real no solo promueve una toma de decisiones más informada en términos de eficiencia energética, sino que también incentiva la adquisición de equipos más eficientes, contribuyendo así al ahorro energético y la reducción del impacto ambiental [13].…”