A Supervised Event-Based Non-Intrusive Load Monitoring for Non-Linear Appliances

Abstract

Smart meters generate a massive volume of energy consumption data which can be analyzed to recover some interesting and beneficial information. Non-intrusive load monitoring (NILM) is one important application fostered by the mass deployment of smart meters. This paper presents a supervised event-based NILM approach for non-linear appliance activities identification. Firstly, the additive properties (stating that, when a certain amount of specific appliances' feature is added to their belonging network, an equal amount of change in the network's feature can be observed) of three features (harmonic feature, voltage-current trajectory feature, and active-reactive-distortion (PQD) power curve features) were investigated through experiments. The results verify the good additive property for the harmonic features and Voltage-Current (U-I) trajectory features. In contrast, PQD power curve features have a poor additive property. Secondly, based on the verified additive property of harmonic current features and the representation of waveforms, a harmonic current features based approach is proposed for NILM, which includes two main processes: event detection and event classification. For event detection, a novel model is proposed based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. Compared to other event detectors, the proposed event detector not only can detect both event timestamp and two adjacent steady states but also shows high detection accuracy over public dataset with F1-score up to 98.99%. Multi-layer perceptron (MLP) classifiers are then built for multi-class event classification using the harmonic current features and are trained using the data collected from the laboratory and the public dataset. The results show that the MLP classifiers have a good performance in classifying non-linear loads. Finally, the proposed harmonic current features based approach is tested in the laboratory through experiments, in which multiple on-off events of multiple appliances occur. The research indicates that clustering-based event detection algorithms are promising for future works in event-based NILM. Harmonic current features have perfect additive property, and MLP classifier using harmonic current features can accurately identify typical non-linear and resistive loads, which could be integrated with other approaches in the future.

NILM Techniques for Intelligent Home Energy Management and Ambient Assisted Living: A Review

“…Techniques such as envelope extraction, advanced filtering, Kalman filter and Hilbert transform are usually involved here in a post-processing stage to achieve suitable event detection and even energy disaggregation [39][40][41]. Clustering and bucketing techniques have also been used in event detection [42].…”

Optimal Strategy to Select Load Identification Features by Using a Particle Resampling Algorithm

“…Load event, which is defined as changes in load characteristics caused by switching on/off or state changes of individual devices [13], is the first and significant step in the load identification. In practical applications, the reliability and accuracy of event detection could be affected by the unpredicted switching and the interference of voltage and current fluctuations.…”

Integration of Demand Response and Photovoltaic Resources in Residential Segments

“…The granularity of data is fixed from 10 to 20 s for a better evaluation of end-uses and to achieve a customer database with multiple possibilities (see for example REDD database in a past paper [34]). For example, this database has been tested for Non-Intrusive Load Monitoring Methodologies (NIALM) through Smart Meter data, for different purposes and loads (the use of NIALM for the disaggregation of main loads can be found previously [29] and for small nonlinear loads in a past paper [39]). This pacer, for monitoring purposes, is of considerable interest in the case of some water heaters with fast switching because demand cycling ranges from 10 to 30 s in some periods.…”

“…In this case, the aggregator or the energy supplier can provide some estimation of WH end-use (see Figure 6) through NIALM [39,54]. The methodology proposed here is to lag or lead the end-use profile of WH, taking into account the changes on demand and customer service, to optimize a specific value, for instance: minimizing net demand, maximizing or minimizing the PV injection to network, minimize the costs of tariffs .…”