{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:39:41Z","timestamp":1781973581523,"version":"3.54.5"},"reference-count":45,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T00:00:00Z","timestamp":1697068800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Liaoning Province Education Administration","award":["LJKZ0174"],"award-info":[{"award-number":["LJKZ0174"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Illicitly obtaining electricity, commonly referred to as electricity theft, is a prominent contributor to power loss. In recent years, there has been growing recognition of the significance of neural network models in electrical theft detection (ETD). Nevertheless, the existing approaches have a restricted capacity to acquire profound characteristics, posing a persistent challenge in reliably and effectively detecting anomalies in power consumption data. Hence, the present study puts forth a hybrid model that amalgamates a convolutional neural network (CNN) and a transformer network as a means to tackle this concern. The CNN model with a dual-scale dual-branch (DSDB) structure incorporates inter- and intra-periodic convolutional blocks to conduct shallow feature extraction of sequences from varying dimensions. This enables the model to capture multi-scale features in a local-to-global fashion. The transformer module with Gaussian weighting (GWT) effectively captures the overall temporal dependencies present in the electricity consumption data, enabling the extraction of sequence features at a deep level. Numerous studies have demonstrated that the proposed method exhibits enhanced efficiency in feature extraction, yielding high F1 scores and AUC values, while also exhibiting notable robustness.<\/jats:p>","DOI":"10.3390\/s23208405","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T03:14:32Z","timestamp":1697080472000},"page":"8405","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Hybrid CNN\u2013Transformer Network for Electricity Theft Detection in Smart Grids"],"prefix":"10.3390","volume":"23","author":[{"given":"Yu","family":"Bai","sequence":"first","affiliation":[{"name":"School of Electronical and Information Engineering, Shenyang Aerospace University, Shenyang 110136, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitong","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Electronical and Information Engineering, Shenyang Aerospace University, Shenyang 110136, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9287-3612","authenticated-orcid":false,"given":"Lili","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronical and Information Engineering, Shenyang Aerospace University, Shenyang 110136, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqi","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronical and Information Engineering, Shenyang Aerospace University, Shenyang 110136, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2589","DOI":"10.1016\/j.renene.2019.08.092","article-title":"A survey on smart grid technologies and applications","volume":"146","author":"Dileep","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/TPWRS.2019.2943115","article-title":"Hybrid deep neural networks for detection of non-technical losses in electricity smart meters","volume":"35","author":"Buzau","year":"2019","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1109\/JSAC.2013.130714","article-title":"A multi-sensor energy theft detection framework for advanced metering infrastructures","volume":"31","author":"McLaughlin","year":"2013","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_4","unstructured":"(2011). Smart Meters Help Reduce Electricity Theft, Increase Safety, BCHydro, Inc.. Available online: https:\/\/www.bchydro.com\/news\/conservation\/2011\/smart_meters_energy_theft.html."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Leite, D., Pessanha, J., Sim\u00f5es, P., Calili, R., and Souza, R. (2020). A stochastic frontier model for definition of non-technical loss targets. Energies, 13.","DOI":"10.3390\/en13123227"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"96334","DOI":"10.1109\/ACCESS.2019.2925322","article-title":"PPETD: Privacy-preserving electricity theft detection scheme with load monitoring and billing for AMI networks","volume":"7","author":"Nabil","year":"2019","journal-title":"IEEE Access"},{"key":"ref_7","first-page":"15","article-title":"A Hybrid Model for Anomalies Detection in AMI System Combining K-means Clustering and Deep Neural Network","volume":"60","author":"Maamar","year":"2019","journal-title":"Comput. Mater. Contin."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Krysanov, V., Danilov, A., Burkovsky, V., Gusev, P., and Gusev, K. (2019, January 17\u201320). Optimization of electric transmission lines (ETL) operation modes based on hardware solutions of process platform FACTS. Proceedings of the 14th International Conference on Electromechanics and Robotics \u201cZavalishin\u2019s Readings\u201d, Kursk, Russia.","DOI":"10.1007\/978-981-13-9267-2_51"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Saeed, M.S., Mustafa, M.W., Hamadneh, N.N., Alshammari, N.A., Sheikh, U.U., Jumani, T.A., Khalid, S.B.A., and Khan, I. (2020). Detection of non-technical losses in power utilities\u2014A comprehensive systematic review. Energies, 13.","DOI":"10.3390\/en13184727"},{"key":"ref_10","unstructured":"Winston, P.H. (1984). Artificial Intelligence, Addison-Wesley Longman Publishing Co., Inc."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2468","DOI":"10.1109\/TSG.2014.2327809","article-title":"Non-cooperative game model applied to an advanced metering infrastructure for non-technical loss screening in micro-distribution systems","volume":"5","author":"Lin","year":"2014","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2453","DOI":"10.1109\/TIFS.2020.2965276","article-title":"Hidden electricity theft by exploiting multiple-pricing scheme in smart grids","volume":"15","author":"Liu","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_13","first-page":"2502928","article-title":"Performance analysis of electricity theft detection for the smart grid: An overview","volume":"71","author":"Yan","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_14","unstructured":"Mitchell, T.M. (1997). Machine Learning, McGraw-Hill."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1126\/science.aaa8415","article-title":"Machine learning: Trends, perspectives, and prospects","volume":"349","author":"Jordan","year":"2015","journal-title":"Science"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Toma, R.N., Hasan, M.N., Nahid, A.A., and Li, B. (2019, January 3\u20135). Electricity theft detection to reduce non-technical loss using support vector machine in smart grid. Proceedings of the 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), Dhaka, Bangladesh.","DOI":"10.1109\/ICASERT.2019.8934601"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1109\/TII.2016.2543145","article-title":"Decision tree and SVM-based data analytics for theft detection in smart grid","volume":"12","author":"Jindal","year":"2016","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.ijepes.2011.09.009","article-title":"Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision trees","volume":"34","author":"Monedero","year":"2012","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_19","first-page":"130","article-title":"Decision tree methods: Applications for classification and prediction","volume":"27","author":"Song","year":"2015","journal-title":"Shanghai Arch. Psychiatry"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Aziz, S., Naqvi, S.Z.H., Khan, M.U., and Aslam, T. (2020, January 26\u201327). Electricity theft detection using empirical mode decomposition and K-nearest neighbors. Proceedings of the IEEE International Conference on Emerging Trends in Smart Technologies (ICETST), Karachi, Pakistan.","DOI":"10.1109\/ICETST49965.2020.9080727"},{"key":"ref_21","unstructured":"Larose, D.T., and Larose, C.D. (2023, August 30). k-Nearest Neighbor Algorithm. Available online: onlinelibrary.wiley.com."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Meira, J.A., Glauner, P., State, R., Valtchev, P., Dolberg, L., Bettinger, F., and Duarte, D. (2017, January 23\u201324). Distilling Provider-Independent Data for General Detection of Non-Technical Losses. Proceedings of the 2017 IEEE Power and Energy Conference at Illinois (PECI), Champaign, IL, USA.","DOI":"10.1109\/PECI.2017.7935765"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7171","DOI":"10.1109\/TPWRS.2018.2853162","article-title":"NTL detection in electric distribution systems using the maximal overlap discrete wavelet-packet transform and random undersampling boosting","volume":"33","author":"Avila","year":"2018","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2661","DOI":"10.1109\/TSG.2018.2807925","article-title":"Detection of non-technical losses using smart meter data and supervised learning","volume":"10","author":"Buzau","year":"2018","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Parmar, A., Katariya, R., and Patel, V. (2018, January 7\u20138). A review on random forest: An ensemble classifier. Proceedings of the International Conference on Intelligent Data Communication Technologies and Internet of Things (ICICI) 2018, Coimbatore, India.","DOI":"10.1007\/978-3-030-03146-6_86"},{"key":"ref_26","first-page":"4136874","article-title":"Electricity theft detection in power grids with deep learning and random forests","volume":"2019","author":"Li","year":"2019","journal-title":"J. Electr. Comput. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1007\/s12525-021-00475-2","article-title":"Machine learning and deep learning","volume":"31","author":"Janiesch","year":"2021","journal-title":"Electr. Mark."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"107085","DOI":"10.1016\/j.ijepes.2021.107085","article-title":"Convolutional neural network applied to detect electricity theft: A comparative study on unbalanced data handling techniques","volume":"131","author":"Pereira","year":"2021","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1606","DOI":"10.1109\/TII.2017.2785963","article-title":"Wide and deep convolutional neural networks for electricity-theft detection to secure smart grids","volume":"14","author":"Zheng","year":"2017","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1007\/s12046-020-01512-0","article-title":"Detection of electricity theft using data processing and LSTM method in distribution systems","volume":"45","author":"Kocaman","year":"2020","journal-title":"S\u0101dhan\u0101"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3428","DOI":"10.1109\/TSG.2020.2973681","article-title":"Deep learning detection of electricity theft cyber-attacks in renewable distributed generation","volume":"11","author":"Ismail","year":"2020","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ullah, A., Javaid, N., Samuel, O., Imran, M., and Shoaib, M. (2020, January 15\u201319). CNN and GRU based deep neural network for electricity theft detection to secure smart grid. Proceedings of the 2020 IEEE International Wireless Communications and Mobile Computing (IWCMC), Limassol, Cyprus.","DOI":"10.1109\/IWCMC48107.2020.9148314"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"141154","DOI":"10.1109\/ACCESS.2021.3119575","article-title":"A novel method CNN-LSTM ensembler based on Black Widow and Blue Monkey Optimizer for electricity theft detection","volume":"9","author":"Almazroi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., and Ding, G. (2021, January 20\u201325). Diverse branch block: Building a convolution as an inception-like unit. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01074"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3231215","article-title":"Spectral\u2013spatial feature tokenization transformer for hyperspectral image classification","volume":"60","author":"Sun","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"108642","DOI":"10.1016\/j.ijepes.2022.108642","article-title":"A novel approach to detect electricity theft based on conv-attentional Transformer Neural Network","volume":"145","author":"Shi","year":"2023","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Kim, J., El-Khamy, M., and Lee, J. (2020, January 4\u20138). T-gsa: Transformer with gaussian-weighted self-attention for speech enhancement. Proceedings of the ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref_38","unstructured":"Nie, Y., Nguyen, N.H., Sinthong, P., and Kalagnanam, J. (2022). A time series is worth 64 words: Long-term forecasting with transformers. arXiv."},{"key":"ref_39","unstructured":"Finardi, P., Campiotti, I., Plensack, G., de Souza, R.D., Nogueira, R., Pinheiro, G., and Lotufo, R. (2020). Electricity theft detection with self-attention. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1109\/TII.2022.3179243","article-title":"Hybrid-order representation learning for electricity theft detection","volume":"19","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_41","first-page":"1","article-title":"A hybrid ConvLSTM-based anomaly detection approach for combating energy theft","volume":"71","author":"Gao","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ding, X., Guo, Y., Ding, G., and Han, J. (2019\u20132, January 27). ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00200"},{"key":"ref_43","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Dempster, A., Schmidt, D.F., and Webb, G.I. (2021, January 14\u201318). Minirocket: A very fast (almost) deterministic transform for time series classification. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual.","DOI":"10.1145\/3447548.3467231"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/20\/8405\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:05:24Z","timestamp":1760130324000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/20\/8405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,12]]},"references-count":45,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["s23208405"],"URL":"https:\/\/doi.org\/10.3390\/s23208405","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,12]]}}}