A New Set of Steady-State and Transient Features for Power Signature Analysis Based on V-I Trajectory

Mulinari, Bruna Machado; Linhares, Robson R.; Campos, Daniel Prado; Costa, Clayton H. da; Ancelmo, Hellen Cristina; Lazzaretti, André E.; Oroski, Elder; Lima, Carlos R. Erig; Renaux, Douglas P. B.; Pöttker, Fabiana

doi:10.1109/isgt-la.2019.8895360

Cited by 21 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the PLAID dataset does not contain subsets with a different number of aggregated loads, in Section 4.2, we present only the results for the approach presented in Figure 1a. For all the experiments in Sections 4.1 and 4.2, we include other two baseline methods for comparisons: (i) V-I trajectory [8] and (ii) Discrete Wavelet Transform (DWT) [48]. Those methods are selected since they are part of the state-of-the-art results presented in [7] and both extract transient and steady-state features, allowing direct comparisons for all experimental scenarios described in Table 3.…”

Section: Resultsmentioning

confidence: 99%

“…The feature extraction stage, which is the main focus here, can be applied for high or low-frequency sampling data. High-frequency techniques reveal more discriminative information, as presented in [8] with Voltage-Current (V-I) trajectories, in [9] with current harmonics, in [10] with wavelet coefficients, and [11] with electromagnetic interference.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Scattering Transform for Classification in Non-Intrusive Load Monitoring

Aguiar

Lazzaretti

Mulinari³

et al. 2021

Energies

View full text Add to dashboard Cite

Nonintrusive Load Monitoring (NILM) uses computational methods to disaggregate and classify electrical appliances signals. The classification is usually based on the power signatures of the appliances obtained by a feature extractor. State-of-the-art results were obtained extracting NILM features with convolutional neural networks (CNN). However, it depends on the training process with large datasets or data augmentation strategies. In this paper, we propose a feature extraction strategy for NILM using the Scattering Transform (ST). The ST is a convolutional network analogous to CNN. Nevertheless, it does not need a training process in the feature extraction stage, and the filter coefficients are analytically determined (not empirically, like CNN). We perform tests with the proposed method on different publicly available datasets and compare the results with state-of-the-art deep learning-based and traditional approaches (including wavelet transform and V-I representations). The results show that ST classification accuracy is more robust in terms of waveform parameters, such as signal length, sampling frequency, and event location. Besides, ST overcame the state-of-the-art techniques for single and aggregated loads (accuracies above 99% for all evaluated datasets), in different training scenarios with single and aggregated loads, indicating its feasibility in practical NILM scenarios.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Scattering Transform for Classification in Non-Intrusive Load Monitoring

Aguiar

Lazzaretti

Mulinari³

et al. 2021

Energies

View full text Add to dashboard Cite

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

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

“…The load signature results from the appliance's working pattern, the conditions in which the devices operate (e.g., temperature and pressure), and the way users manipulate the devices (e.g., time of use and power levels) [1] . A method to represent an appliance's load signature is feature extraction [2] . This dataset has load signatures with seven features for eight common end-uses: refrigerator, stove, dryer, lighting, water heating, air conditioning, microwave, and washing machine.…”

Section: Data Descriptionmentioning

confidence: 99%