{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:03:14Z","timestamp":1774602194217,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>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\u2019 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\u2013frequency 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.<\/jats:p>","DOI":"10.3390\/fi16120436","type":"journal-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T04:21:36Z","timestamp":1732249296000},"page":"436","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["An Ensemble Deep CNN Approach for Power Quality Disturbance Classification: A Technological Route Towards Smart Cities Using Image-Based Transfer"],"prefix":"10.3390","volume":"16","author":[{"given":"Mirza Ateeq Ahmed","family":"Baig","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Mirpur University of Science & Technology (MUST), Mirpur 10250, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3355-6174","authenticated-orcid":false,"given":"Naeem Iqbal","family":"Ratyal","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Mirpur University of Science & Technology (MUST), Mirpur 10250, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2199-5989","authenticated-orcid":false,"given":"Adil","family":"Amin","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Mirpur University of Science & Technology (MUST), Mirpur 10250, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2346-556X","authenticated-orcid":false,"given":"Umar","family":"Jamil","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Texas at San Antonio (UTSA), San Antonio, TX 78249, USA"}]},{"given":"Sheroze","family":"Liaquat","sequence":"additional","affiliation":[{"name":"Eaton Research Labs, Eaton Corporation, Golden, CO 80401, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1136-6433","authenticated-orcid":false,"given":"Haris M.","family":"Khalid","sequence":"additional","affiliation":[{"name":"College of Engineering and Information Technology, University of Dubai, Dubai 14143, United Arab Emirates"},{"name":"Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg 2006, South Africa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8654-6121","authenticated-orcid":false,"given":"Muhammad Fahad","family":"Zia","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, American University in Dubai, Dubai 28282, United Arab Emirates"}]}],"member":"1968","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.ref.2018.12.002","article-title":"A new robust kernel ridge regression classifier for islanding and power quality disturbances in a multi distributed generation based microgrid","volume":"28","author":"Chakravorti","year":"2019","journal-title":"Renew. Energy Focus"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"109020","DOI":"10.1016\/j.epsr.2022.109020","article-title":"Towards technical and economic feasibility of power quality compensators","volume":"216","author":"Conrado","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, H., Wang, D., and Bi, T. (2021). Classification of power quality disturbance based on S-transform and convolution neural network. Front. Energy Res., 9.","DOI":"10.3389\/fenrg.2021.708131"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Priyadarshini, M., Bajaj, M., Prokop, L., and Berhanu, M. (2024). Perception of power quality disturbances using Fourier, Short-Time Fourier, continuous and discrete wavelet transforms. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-53792-9"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, S., Li, Z., Pan, G., and Xu, F. (2022). Power quality disturbance recognition using empirical wavelet transform and feature selection. Electronics, 11.","DOI":"10.3390\/electronics11020174"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.A., Sotomonte, J.F., Cifuentes, J., and Bueno-L\u00f3pez, M. (2019, January 9\u201311). 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), Porto, Portugal.","DOI":"10.1109\/SEST.2019.8849114"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Dutt, P.V.B.P., and Balaga, H. (2022, January 28\u201329). 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, Jaipur, India.","DOI":"10.1007\/978-981-99-4795-9_1"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MSP.2017.2743842","article-title":"Challenges and open problems in signal processing: Panel discussion summary from ICASSP 2017 [panel and forum]","volume":"34","author":"Eldar","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ijaz, M., Shafiullah, M., and Abido, M. (2015, January 11\u201316). 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), Porto, Portugal.","DOI":"10.1109\/ISAP.2015.7325522"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TII.2015.2486379","article-title":"Feature extraction and power quality disturbances classification using smart meters signals","volume":"12","author":"Borges","year":"2015","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"173530","DOI":"10.1109\/ACCESS.2020.3025190","article-title":"Recognition of complex power quality disturbances using S-transform based ruled decision tree","volume":"8","author":"Mahela","year":"2020","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e2286","DOI":"10.1002\/etep.2286","article-title":"Detection and classification of complex power quality disturbances using S-transform amplitude matrix\u2013based decision tree for different noise levels","volume":"27","author":"Loganathan","year":"2017","journal-title":"Int. Trans. Electr. Energy Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3997","DOI":"10.1109\/TII.2017.2785321","article-title":"Three-layer Bayesian network for classification of complex power quality disturbances","volume":"14","author":"Luo","year":"2017","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_14","first-page":"1236","article-title":"Estimation of power quality in distribution system using fuzzy logic theory","volume":"323","author":"Saleem","year":"2023","journal-title":"Indones. J. Electr. Eng. Comput. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"6951","DOI":"10.1109\/TSG.2017.2771146","article-title":"Intelligent expert system for power quality improvement under distorted and unbalanced conditions in three-phase AC microgrids","volume":"9","author":"Moreira","year":"2017","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.neucom.2019.01.038","article-title":"A classification method for multiple power quality disturbances using EWT based adaptive filtering and multiclass SVM","volume":"334","author":"Thirumala","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e2303","DOI":"10.1002\/etep.2303","article-title":"An implementation of type-2 fuzzy kernel based support vector machine algorithm for power quality events classification","volume":"27","author":"Naderian","year":"2017","journal-title":"Int. Trans. Electr. Energy Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dekhandji, F.Z., Recioui, A., Ladada, A., and Moulay Brahim, T.S. (2023). Detection and Classification of Power Quality Disturbances Using LSTM. Eng. Proc., 29.","DOI":"10.3390\/engproc2023029002"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s00202-022-01667-5","article-title":"LSTM power quality disturbance classification with wavelets and attention mechanism","volume":"105","author":"Chiam","year":"2023","journal-title":"Electr. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1126","DOI":"10.1016\/j.apenergy.2018.09.160","article-title":"A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network","volume":"235","author":"Wang","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Perez-Anaya, E., Jaen-Cuellar, A.Y., Elvira-Ortiz, D.A., Romero-Troncoso, R.d.J., and Saucedo-Dorantes, J.J. (2024). Methodology for the Detection and Classification of Power Quality Disturbances Using CWT and CNN. Energies, 17.","DOI":"10.3390\/en17040852"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s11370-021-00358-7","article-title":"Combining CNN and LSTM for activity of daily living recognition with a 3D matrix skeleton representation","volume":"14","author":"Ercolano","year":"2021","journal-title":"Intell. Serv. Robot."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Mohan, N., Soman, K., and Vinayakumar, R. (2017, January 21\u201323). Deep power: Deep learning architectures for power quality disturbances classification. Proceedings of the 2017 International Conference on Technological Advancements in Power and Energy (TAP Energy), Kollam, India.","DOI":"10.1109\/TAPENERGY.2017.8397249"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"108695","DOI":"10.1016\/j.epsr.2022.108695","article-title":"Ensemble deep learning for automated classification of power quality disturbances signals","volume":"213","author":"Wang","year":"2022","journal-title":"Electr. Power Syst. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.aej.2023.03.006","article-title":"Efficient online detection system of power disturbances based on deep-learning approach","volume":"70","author":"Shouman","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"121011","DOI":"10.1016\/j.apenergy.2023.121011","article-title":"A novel dual-attention optimization model for points classification of power quality disturbances","volume":"339","author":"Liu","year":"2023","journal-title":"Appl. Energy"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Manikonda, S.K., Santhosh, J., Sreekala, S.P.K., Gangwani, S., and Gaonkar, D.N. (2019, January 11\u201313). Power quality event classification using transfer learning on images. Proceedings of the 2019 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), Tamilnadu, India.","DOI":"10.1109\/INCOS45849.2019.8951370"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"108795","DOI":"10.1016\/j.epsr.2022.108795","article-title":"An image-based deep transfer learning approach to classify power quality disturbances","volume":"213","author":"Todeschini","year":"2022","journal-title":"Electr. Power Syst. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"109369","DOI":"10.1016\/j.epsr.2023.109369","article-title":"PQEventCog: Classification of power quality disturbances based on optimized S-transform and CNNs with noisy labeled datasets","volume":"220","author":"Fu","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"109025","DOI":"10.1016\/j.measurement.2021.109025","article-title":"A stacking ensemble classification model for detection and classification of power quality disturbances in PV integrated power network","volume":"175","author":"Radhakrishnan","year":"2021","journal-title":"Measurement"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Dhalaria, M., Gandotra, E., and Saha, S. (2019, January 12\u201313). Comparative analysis of ensemble methods for classification of android malicious applications. Proceedings of the Advances in Computing and Data Sciences: Third International Conference, ICACDS 2019, Ghaziabad, India.","DOI":"10.1007\/978-981-13-9939-8_33"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"10351","DOI":"10.1007\/s00500-019-04538-7","article-title":"Detection and classification of power quality disturbances or events by adaptive NFS classifier","volume":"24","author":"Kiruthiga","year":"2020","journal-title":"Soft Comput."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"114785","DOI":"10.1016\/j.eswa.2021.114785","article-title":"A novel hybrid deep learning approach including combination of 1D power signals and 2D signal images for power quality disturbance classification","volume":"174","author":"Sindi","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"107245","DOI":"10.1016\/j.engappai.2023.107245","article-title":"Adversarial attack and training for deep neural network based power quality disturbance classification","volume":"127","author":"Zhang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"108834","DOI":"10.1016\/j.epsr.2022.108834","article-title":"The use of deep learning and 2-D wavelet scalograms for power quality disturbances classification","volume":"214","author":"Salles","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"107152","DOI":"10.1016\/j.epsr.2021.107152","article-title":"Open source dataset generator for power quality disturbances with deep-learning reference classifiers","volume":"195","author":"Machlev","year":"2021","journal-title":"Electr. Power Syst. Res."},{"key":"ref_37","unstructured":"(1995). IEEE Recommended Practice for Monitoring Electric Power Quality (Standard No. 1159-1995)."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"110181","DOI":"10.1016\/j.asoc.2023.110181","article-title":"Classification of power quality disturbances using linear discriminant analysis","volume":"138","author":"Singh","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_39","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_40","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_41","first-page":"84","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_42","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv."},{"key":"ref_43","first-page":"8706505","article-title":"Comparison of data mining classification algorithms determining the default risk","volume":"2019","year":"2019","journal-title":"Sci. Program."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"110260","DOI":"10.1016\/j.measurement.2021.110260","article-title":"A power quality detection and classification algorithm based on FDST and hyper-parameter tuned light-GBM using memetic firefly algorithm","volume":"187","author":"Panigrahi","year":"2022","journal-title":"Measurement"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"108493","DOI":"10.1109\/ACCESS.2023.3321301","article-title":"Power quality in microgrids: A critical review of fundamentals, standards, and case studies","volume":"11","author":"Sepasi","year":"2023","journal-title":"IEEE Access"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Balouji, E., and Salor, O. (2017, January 19\u201320). Classification of power quality events using deep learning on event images. Proceedings of the 2017 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA), Shahrekord, Iran.","DOI":"10.1109\/PRIA.2017.7983049"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Minh Khoa, N., and Van Dai, L. (2020). Detection and classification of power quality disturbances in power system using modified-combination between the stockwell transform and decision tree methods. Energies, 13.","DOI":"10.3390\/en13143623"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, P., and Liu, T. (2017). Power quality disturbance classification using the S-transform and probabilistic neural network. Energies, 10.","DOI":"10.3390\/en10010107"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/16\/12\/436\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:37:15Z","timestamp":1760114235000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/16\/12\/436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":48,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["fi16120436"],"URL":"https:\/\/doi.org\/10.3390\/fi16120436","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]}}}