Non-Intrusive Load Monitoring: an Architecture and its evaluation for Power Electronics loads

Renaux, Douglas P. B.; Lima, Carlos R. Erig; Pöttker, Fabiana; Oroski, Elder; Lazzaretti, André E.; Linhares, Robson R.; Almeida, Andressa R.; Coelho, Adil O.; Hercules, Mateus C.

doi:10.1109/peac.2018.8590472

Cited by 9 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table IV, the proposed method presents an improvement of Accuracy of 8.67% in relation to [33], 0.54% to [34], and 2.02% in relation to [35].…”

Section: Comparisons With State-of-the-art Approachesmentioning

confidence: 86%

Performance of Scattering Transform Feature Extraction for Electrical Load Classification

Aguiar¹,

Lazzaretti²,

Pipa³

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

The Scattering transform (ST) presents itself as an alternative approach to the classic methods that involve neural networks and deep learning techniques for the feature extraction and classification of signals and images. Among its main advantages, one can emphasize that the coefficients of the ST are determined analytically and do not need to be learned, as typically performed in Convolutional Neural Networks (CNNs). Additionally, ST has time-shifting and small time-warping invariance, which reduces the need for precise temporal localization (detection) for subsequent classification. This paper originally proposes the application of ST to extract features and classify Non-intrusive Load Monitoring (NILM) high-frequency signals. We validate the extraction strategy performance varying several parameters for ST calculation, such as signal length, number of examples, and sampling frequency. The results outperform other state-of-the-art feature extraction techniques, reaching up to 99.98% of accuracy and 99.51% of FScore for a publicly available dataset, demonstrating the feasibility and promising aspects of the ST for NILM problems.

show abstract

“…As shown in Table IV, the proposed method presents an improvement of Accuracy of 8.67% in relation to [33], 0.54% to [34], and 2.02% in relation to [35].…”

Section: Comparisons With State-of-the-art Approachesmentioning

confidence: 86%

Performance of Scattering Transform Feature Extraction for Electrical Load Classification

Aguiar¹,

Lazzaretti²,

Pipa³

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…In this case, from a comparison between the real and the estimated signal, the higher number of errors in the latter is usually related to the signal regions where more changes occur, which are usually transients. One last detection approach uses vectorization [13], [14] to characterize the samples of a signal into "valid" and "non-valid" states. Non-valid states are associated with events such as abrupt transitions, high derivatives values or highfrequency oscillations, which resemble the turn-on and off conditions that we are looking for.…”

Section: Related Workmentioning

confidence: 99%

An Embedded System for NILM Using Machine Learning

Braglia¹,

Lazzaretti²

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

The interest in power managing systems has been growing in recent years since every industrial or domestic plant moves towards techniques to efficiently reduce energy demand and costs related to it. An attractive solution is represented by Non-Intrusive Load Monitoring (NILM) systems, whose primary purpose is to find a more appropriate way of keeping track of the power consumption caused by each of the loads that are connected to the monitored plant. A possible real-life implementation of a NILM system is addressed in this work, discussing all the fundamental blocks in its structure, including detecting events, feature extraction, and load classification, using publicly available datasets. Additionally, we provide a solution for an embedded system, able to analyze aggregated waveforms and to recognize each appliance’s contribution in it. The main algorithm, its features, drawbacks, and implementation are thus explained, showing current and future challenges for the final application.

show abstract

“…The LIT-Dataset is composed of three different subsets: Synthetic [31], Simulated [32], and Natural [33]. In the Synthetic subset data is collected using a 1 kW jig to switch up to eight loads on and off, in a programmable pattern.…”

Section: Lit-datasetmentioning

confidence: 99%

A Multi-Agent NILM Architecture for Event Detection and Load Classification

et al. 2020

Self Cite

View full text Add to dashboard Cite

A multi-agent architecture for a Non-Intrusive Load Monitoring (NILM) solution is presented and evaluated. The underlying rationale for such an architecture is that each agent (load event detection, feature extraction, and classification) outperforms others of the same type in particular scenarios; hence, by combining the expertise of these agents, the system presents an improved performance. Known NILM algorithms, as well as new algorithms, proposed by the authors, were individually evaluated and compared. The proposed architecture considers a NILM system composed of Load Monitoring Modules (LMM) that report to a Center of Operations, required in larger facilities. For the purposed of evaluating and comparing performance, five load event detect agents, five feature extraction agents, and five classification agents were studied so that the best combinations of agents could be implemented in LMMs. To evaluate the proposed system, the COOLL and the LIT-Dataset were used. Performance improvements were detected in all scenarios, with power-ON and power-OFF detection improving up to 13%, while classification accuracy improved up to 9.4%.

show abstract

Non-Intrusive Load Monitoring: an Architecture and its evaluation for Power Electronics loads

Cited by 9 publications

References 9 publications

Performance of Scattering Transform Feature Extraction for Electrical Load Classification

Performance of Scattering Transform Feature Extraction for Electrical Load Classification

An Embedded System for NILM Using Machine Learning

A Multi-Agent NILM Architecture for Event Detection and Load Classification

Contact Info

Product

Resources

About