An Ensemble Deep CNN Approach for Power Quality Disturbance Classification: A Technological Route Towards Smart Cities Using Image-Based Transfer

被引：0

作者：

Baig, Mirza Ateeq Ahmed ^{[1
]}

Ratyal, Naeem Iqbal ^{[1
]}

Amin, Adil ^{[1
]}

Jamil, Umar ^{[2
]}

Liaquat, Sheroze ^{[3
]}

Khalid, Haris M. ^{[4
,5
]}

Zia, Muhammad Fahad ^{[6
]}

机构：

[1] Department of Electrical Engineering, Mirpur University of Science & Technology (MUST), Mirpur

[2] Department of Electrical and Computer Engineering, University of Texas at San Antonio (UTSA), San Antonio, 78249, TX

[3] Eaton Research Labs, Eaton Corporation, Golden, 80401, CO

[4] College of Engineering and Information Technology, University of Dubai, Dubai

[5] Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg

[6] Department of Electrical and Computer Engineering, American University in Dubai, Dubai

来源：

Future Internet | 2024年 / 16卷 / 12期

关键词：

deep convolution neural networks; deep learning; ensemble learning; machine learning; power quality disturbances; revolutionary technologies; smart cities; transfer learning;

D O I：

10.3390/fi16120436

中图分类号：

学科分类号：

摘要：

The abundance of powered semiconductor devices has increased with the introduction of renewable energy sources into the grid, causing power quality disturbances (PQDs). This represents a huge challenge for grid reliability and smart city infrastructures. Accurate detection and classification are important for grid reliability and consumers’ appliances in a smart city environment. Conventionally, power quality monitoring relies on trivial machine learning classifiers or signal processing methods. However, recent advancements have introduced Deep Convolution Neural Networks (DCNNs) as promising methods for the detection and classification of PQDs. These techniques have the potential to demonstrate high classification accuracy, making them a more appropriate choice for real-time operations in a smart city framework. This paper presents a voting ensemble approach to classify sixteen PQDs, using the DCNN architecture through transfer learning. In this process, continuous wavelet transform (CWT) is employed to convert one-dimensional (1-D) PQD signals into time–frequency images. Four pre-trained DCNN architectures, i.e., Residual Network-50 (ResNet-50), Visual Geometry Group-16 (VGG-16), AlexNet and SqeezeNet are trained and implemented in MATLAB, using images of four datasets, i.e., without noise, 20 dB noise, 30 dB noise and random noise. Additionally, we also tested the performance of ResNet-50 with a squeeze-and-excitation (SE) mechanism. It was observed that ResNet-50 with the SE mechanism has a better classification accuracy; however, it causes computational overheads. The classification performance is enhanced by using the voting ensemble model. The results indicate that the proposed scheme improved the accuracy (99.98%), precision (99.97%), recall (99.80%) and F1-score (99.85%). As an outcome of this work, it is demonstrated that ResNet-50 with the SE mechanism is a viable choice as a single classification model, while an ensemble approach further increases the generalized performance for PQD classification. © 2024 by the authors.

引用

共 48 条

[1] Chakravorti T., Nayak N., Bisoi R., Dash P., Tripathy L., A new robust kernel ridge regression classifier for islanding and power quality disturbances in a multi distributed generation based microgrid, Renew. Energy Focus, 28, pp. 78-99, (2019)
[2] Conrado B.R., de Souza W.A., Liberado E.V., Paredes H.K., Brandao D.I., Moreira A.C., Towards technical and economic feasibility of power quality compensators, Electr. Power Syst. Res, 216, (2023)
[3] Li J., Liu H., Wang D., Bi T., Classification of power quality disturbance based on S-transform and convolution neural network, Front. Energy Res, 9, (2021)
[4] Priyadarshini M., Bajaj M., Prokop L., Berhanu M., Perception of power quality disturbances using Fourier, Short-Time Fourier, continuous and discrete wavelet transforms, Sci. Rep, 14, (2024)
[5] Chen S., Li Z., Pan G., Xu F., Power quality disturbance recognition using empirical wavelet transform and feature selection, Electronics, 11, (2022)
[6] Rodriguez M.A., Sotomonte J.F., Cifuentes J., Bueno-Lopez M., Classification of power quality disturbances using hilbert huang transform and a multilayer perceptron neural network model, Proceedings of the 2019 International Conference on Smart Energy Systems and Technologies (SEST), pp. 1-6, (2019)
[7] Dutt P.V.B.P., Balaga H., Detection and Classification of Power Quality Disturbances Using Variational Mode Decomposition and Deep Learning Networks, Proceedings of the International Conference on Flexible Electronics for Electric Vehicles, pp. 1-12, (2022)
[8] Eldar Y.C., Hero A.O., Deng L., Fessler J., Kovacevic J., Poor H.V., Young S., Challenges and open problems in signal processing: Panel discussion summary from ICASSP 2017 [panel and forum], IEEE Signal Process. Mag, 34, pp. 8-23, (2017)
[9] Ijaz M., Shafiullah M., Abido M., Classification of power quality disturbances using Wavelet Transform and Optimized ANN, Proceedings of the 2015 18th International Conference on Intelligent System Application to Power Systems (ISAP), pp. 1-6, (2015)
[10] Borges F.A., Fernandes R.A., Silva I.N., Silva C.B., Feature extraction and power quality disturbances classification using smart meters signals, IEEE Trans. Ind. Inform, 12, pp. 824-833, (2015)

← 1 2 3 4 5 →