Disaggregation of the electric loads of small customers through the application of the Hilbert transform

Gabaldón, A.; Ortiz, Mario; Molina, Roque; Verdú, S.

doi:10.1007/s12053-013-9250-6

Cited by 13 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They reached the best accuracy with 81.75% using random forest algorithm over PLAID dataset. Some transformations of time-series signals were conducted to shed light on feature engineering including Fourier transformation [25], Wavelet Packet transformation [42], Stockwell transformation [43,44] and Hilbert transformation [45]. Fourier transformation of features are well-known for harmonic vectors or harmonic spectrogram.…”

Section: Features and Features Additive Propertymentioning

confidence: 99%

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

2018

View full text Add to dashboard Cite

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.

show abstract

Section: Features and Features Additive Propertymentioning

confidence: 99%

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

2018

View full text Add to dashboard Cite

show abstract

“…In power systems, a refinement of HT, Hilbert-Huang Transform (HHT), has helped to solve other problems [25,26]. In [27], HT is used to extract the individual demand for water heater and electric heater from aggregated demand for energy efficiency and DR uses through the use of the analytic signal s(t). Some problems of this approach are that errors from 10% to 15% in power are reported, and moreover, the fact that only the two loads with highest amplitudes are extracted.…”

Section: Load Disaggregationmentioning

confidence: 99%

“…Therefore, to extract the information contained in an aggregated signal, a different and direct approach had to be developed. The proposed method is based on the approach presented in [27] but performs a modified and improved decomposition and filtering method. The advantages and characteristics of the proposed method are as follows.…”

Section: Demodulation and Filtering Of Pulse Waveforms 41 Ht Principlementioning

confidence: 99%

“…1) It is based on the properties of HT and not only in the values of s(t): this allows a better performance of 2) The amplitude of each signal is evaluated through reconstruction and filtering through inverse transform. This allows to bound the errors in amplitude (from 10%-15% in [27] to 5% in the proposed method).…”

Section: Demodulation and Filtering Of Pulse Waveforms 41 Ht Principlementioning

confidence: 99%

“…For applying HT, the signal must comply with the IMF conditions. Although this is often true, reference [27] demonstrates that the signal does not have to be an IMF.…”

Section: Demodulation and Filtering Of Pulse Waveforms 41 Ht Principlementioning

confidence: 99%

See 2 more Smart Citations

Residential end-uses disaggregation and demand response evaluation using integral transforms

Gabaldón

Molina

Marín-Parra

et al. 2016

J. Mod. Power Syst. Clean Energy

Self Cite

View full text Add to dashboard Cite

Demand response is a basic tool used to develop modern power systems and electricity markets. Residential and commercial segments account for 40%-50% of the overall electricity demand. These segments need to overcome major obstacles before they can be included in a demand response portfolio. The objective of this paper is to tackle some of the technical barriers and explain how the potential of enabling technology (smart meters) can be harnessed, to evaluate the potential of customers for demand response (end-uses and their behaviors) and, moreover, to validate customers' effective response to market prices or system events by means of non-intrusive methods. A tool based on the Hilbert transform is improved herein to identify and characterize the most suitable loads for the aforesaid purpose, whereby important characteristics such as cycling frequency, power level and pulse width are identified. The proposed methodology allows the filtering of aggregated load according to the amplitudes of elemental loads, independently of the frequency of their behaviors that could be altered by internal or external inputs such as weather or demand response. In this way, the assessment and verification of customer response can be improved by solving the problem of load aggregation with the help of integral transforms.

show abstract

Introduction

Liu

2020

Smart Device Recognition

View full text Add to dashboard Cite

Disaggregation of the electric loads of small customers through the application of the Hilbert transform

Cited by 13 publications

References 18 publications

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

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

Residential end-uses disaggregation and demand response evaluation using integral transforms

Introduction

Contact Info

Product

Resources

About