Е-Публикации
Технически университет - София

Abstract: This study proposes a hybrid deep learning framework that integrates supervised classification and unsupervised profiling for electricity consumption analysis. In the supervised phase, a one-dimensional Convolutional Neural Network combined with Long Short-Term Memory (1D CNN–LSTM) architecture is developed to classify daily load patterns. The performance of the proposed model is compared with traditional machine learning and deep learning approaches, including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), a standalone Long Short-Term Memory (LSTM) model, a Transformer-based model, and a standalone 1D CNN model. Experimental results on the Precon house dataset and the CU-BEMS dataset demonstrate that the proposed hybrid architecture outperforms the benchmark models, achieving classification accuracies of 87.59% and 86.40%, respectively. In the unsupervised phase, the trained CNN–LSTM encoder is utilized as a deep feature extractor. The resulting 32-dimensional latent embeddings are clustered using K-Means, Gaussian Mixture Model (GMM), Agglomerative, Spectral, and Ensemble methods. Clustering robustness is evaluated through bootstrap-based stability analysis using the Adjusted Rand Index (ARI) and the Normalized Mutual Information (NMI). The results demonstrate stable and interpretable electricity consumption profiles, particularly in the residential dataset, where near-perfect clustering stability is observed for K-Means. The proposed framework provides both improved classification performance and robust consumption profiling based on deep embedding, offering a practical tool for energy management.

References

1. Ahmed M. Usman M. Wang Z. Ahmad M. The Effect of Energy Consumption, Income, and Population Growth on CO2Emissions: Evidence from NARDL and Machine Learning Models Sustainability 2023 15 11956 10.3390/su151511956
2. Chung J. Jang B. Accurate Prediction of Electricity Consumption Using a Hybrid CNN-LSTM Model Based on Multivariable Data PLoS ONE 2022 17 e0278071 10.1371/journal.pone.0278071 36417448
3. Kim T.Y. Cho S.B. Predicting the Household Power Consumption Using CNN-LSTM Hybrid Networks International Conference on Intelligent Data Engineering and Automated Learning Lecture Notes in Computer Science Springer International Publishing Cham, Switzerland 2018 Volume 11306 481 490 10.1007/978-3-030-03493-1_50
4. Saleem M.U. Ahmad A. Shah A. Mehmood A. Musaddiq A. Integrating Smart Energy Management System with Internet of Things and Cloud Computing for Efficient Demand Side Management in Smart Grids Energies 2023 16 4835 10.3390/en16124835
5. Mischos S. Dalagdi E. Vrakas D. Intelligent Energy Management Systems: A Review Artif. Intell. Rev. 2023 56 11635 11674 10.1007/s10462-023-10441-3
6. Yang D. Guo J.E. Li J. Wang S. Sun S. Knowledge Mapping in Electricity Demand Forecasting: A Scientometric Insight Front. Energy Res. 2021 9 771433 10.3389/fenrg.2021.771433
7. Li Y. Energy Consumption Forecasting with Deep Learning J. Phys. Conf. Ser. 2024 2711 012012 10.1088/1742-6596/2711/1/012012
8. Viegas J.L. Vieira S.M. Sousa J.M. Melício R. Mendes V.M.F. Electricity Demand Profile Prediction Based on Household Characteristics Proceedings of the 2015 12th International Conference on the European Energy Market (EEM), Lisbon, Portugal, 19–22 May 2015 IEEE New York, NY, USA 2015 1 5 10.1109/EEM.2015.7216721
9. Li D. Bissyandé T.F. Kubler S. Klein J. Le Traon Y. Profiling Household Appliance Electricity Usage with N-Gram Language Modeling Proceedings of the 2016 IEEE International Conference on Industrial Technology (ICIT), Taipei, Taiwan, 14–17 March 2016 IEEE New York, NY, USA 2016 604 609 10.1109/ICIT.2016.7474818
10. Viegas J.L. Vieira S.M. Melício R. Mendes V.M.F. Sousa J.M.C. Classification of New Electricity Customers Based on Surveys and Smart Metering Data Energy 2016 107 804 817 10.1016/j.energy.2016.04.065
11. Jiang Z. Lin R. Yang F. A Hybrid Machine Learning Model for Electricity Consumer Categorization Using Smart Meter Data Energies 2018 11 2235 10.3390/en11092235
12. Chavda R. Pandya S.D. Kotwal C.D. Electricity Consumption Patterns Using SOM-Based Two-Level Clustering of Residential Households Indian J. Comput. Sci. Eng. 2022 13 93 107 10.21817/indjcse/2022/v13i1/221301084
13. Buitrago J. Abdulaal A. Asfour S. Electric Load Pattern Classification Using Parameter Estimation, Clustering and Artificial Neural Networks Int. J. Power Energy Syst. 2015 4 167 174 Available online: https://www.researchgate.net/publication/292175905_Electric_load_pattern_classification_using_parameter_estimation_clustering_and_artificial_neural_networks (accessed on 12 November 2025) 10.2316/Journal.203.2015.4.203-6216
14. Hernández L. Baladrón C. Aguiar J.M. Carro B. Sánchez-Esguevillas A. Classification and Clustering of Electricity Demand Patterns in Industrial Parks Energies 2012 5 5215 5228 10.3390/en5125215
15. Tsekouras G.J. Hatziargyriou N.D. Dialynas E.N. Two-Stage Pattern Recognition of Load Curves for Classification of Electricity Customers IEEE Trans. Power Syst. 2007 22 1120 1128 10.1109/TPWRS.2007.901287
16. Hopf K. Sodenkamp M. Kozlovkiy I. Staake T. Feature Extraction and Filtering for Household Classification Based on Smart Electricity Meter Data Comput. Sci. Res. Dev. 2016 31 141 148 10.1007/s00450-014-0294-4
17. Kim H. Park S. Kim S. Time-Series Clustering and Forecasting Household Electricity Demand Using Smart Meter Data Energy Rep. 2023 9 4111 4121 10.1016/j.egyr.2023.03.042
18. Kaur R. Gabrijelčič D. Behavior Segmentation of Electricity Consumption Patterns: A Cluster Analytical Approach Knowl. Based Syst. 2022 251 109236 10.1016/j.knosys.2022.109236
19. McLoughlin F. Duffy A. Conlon M. A Clustering Approach to Domestic Electricity Load Profile Characterisation Using Smart Metering Data Appl. Energy 2015 141 190 199 10.1016/j.apenergy.2014.12.039
20. Irankhah A. Rezazadeh S. Moghaddam M.H.Y. Ershadi-Nasab S. Hybrid Deep Learning Method Based on LSTM-Autoencoder Network for Household Short-Term Load Forecasting Proceedings of the 2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS), Tehran, Iran, 29–30 December 2021 IEEE New York, NY, USA 2021 10.1109/ICSPIS54653.2021.9729378
21. Ibrahim N.M. Megahed A.I. Abbasy N.H. Short-Term Individual Household Load Forecasting Framework Using LSTM Deep Learning Approach Proceedings of the 2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Ankara, Turkey, 21–23 October 2021 IEEE New York, NY, USA 2021 257 262 10.1109/ISMSIT52890.2021.9604650
22. Bedi J. Toshniwal D. Deep Learning Framework to Forecast Electricity Demand Appl. Energy 2019 238 1312 1326 10.1016/j.apenergy.2019.01.113
23. Amber K.P. Ahmad R. Aslam M.W. Kousar A. Usman M. Khan M.S. Intelligent Techniques for Forecasting Electricity Consumption of Buildings Energy 2018 157 886 893 10.1016/j.energy.2018.05.155
24. Syed D. Abu-Rub H. Ghrayeb A. Refaat S.S. Household-Level Energy Forecasting in Smart Buildings Using a Novel Hybrid Deep Learning Model IEEE Access 2021 9 33498 33511 10.1109/ACCESS.2021.3061370
25. Yaslan Y. Bican B. Empirical Mode Decomposition Based Denoising Method with Support Vector Regression for Time Series Prediction: A Case Study for Electricity Load Forecasting Measurement 2017 103 52 61 10.1016/j.measurement.2017.02.007
26. Ridwana I. Nassif N. Choi W. Modeling of Building Energy Consumption by Integrating Regression Analysis and Artificial Neural Network with Data Classification Buildings 2020 10 198 10.3390/buildings10110198
27. Kardi M. AlSkaif T. Tekinerdogan B. Catalão J.P.S. Anomaly Detection in Electricity Consumption Data Using Deep Learning Proceedings of the 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), Bari, Italy, 7–10 September 2021 IEEE New York, NY, USA 2021 10.1109/EEEIC/ICPSEurope51590.2021.9584650
28. Alraddadi G.H. Othman M.T.B. Development of an Efficient Electricity Consumption Prediction Model Using Machine Learning Techniques Int. J. Adv. Comput. Sci. Appl. 2022 13 376 385 10.14569/IJACSA.2022.0130147
29. Wang C. Bäck T. Automated Machine Learning for Short-Term Electric Load Forecasting Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China, 6–9 December 2019 IEEE New York, NY, USA 2019 10.1109/SSCI44817.2019.9002839
30. Babu U.R. Kumar N. Padmaja K. Bhoopathy V. Alam M.S. Devi S.R. Predicting Electricity Consumption in Commercial and Residential Buildings Using A-CNN-LSTM Model Proceedings of the 2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS), Hassan, India, 23–24 August 2024 IEEE New York, NY, USA 2024 10.1109/IACIS61494.2024.10721849
31. Al-Saudi K. Degeler V. Medema M. Energy Consumption Patterns and Load Forecasting with Profiled CNN-LSTM Networks Processes 2021 9 1870 10.3390/pr9111870
32. Ramnath G.S. Harikrishnan R. Muyeen S.M. Kotecha K. Household Electricity Consumer Classification Using Novel Clustering Approach, Review, and Case Study Electronics 2022 11 2302 10.3390/electronics11152302
33. Alhussein M. Aurangzeb K. Haider S.I. Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting IEEE Access 2020 8 180544 180557 10.1109/ACCESS.2020.3028281
34. Michalakopoulos V. Sarmas E. Papias I. Skaloumpakas P. Marinakis V. Doukas H. A Machine Learning-Based Framework for Clustering Residential Electricity Load Profiles to Enhance Demand Response Programs Appl. Energy 2024 361 122943 10.1016/j.apenergy.2024.122943
35. Wu W. Deng Q. Shan X. Miao L. Wang R. Ren Z. Short-Term Forecasting of Daily Electricity of Different Campus Building Clusters Based on a Combined Forecasting Model Buildings 2023 13 2721 10.3390/buildings13112721
36. Zhou Y. Ren B. Xue X. Chen L. Building Energy Consumption Forecasting Based on K-Shape Clustering and CNN-LSTM Proceedings of the 2022 4th International Conference on Power and Energy Technology (ICPET), Beijing, China, 28–31 July 2022 IEEE New York, NY, USA 2022 1147 1152 10.1109/ICPET55165.2022.9918219
37. Gabrielski J. Hager U. Salazar E. Samper M. Rosero V. Real Data-Driven Demand Forecasting and Clustering for Price Planning Proceedings of the 2024 IEEE Power & Energy Society General Meeting (PESGM), Seattle, WA, USA, 21–25 July 2024 IEEE New York, NY, USA 2024 10.1109/PESGM51994.2024.10688987
38. Energy Informatics Group @ LUMS PRECON Electricity Consumption Dataset 2025 Available online: https://web.lums.edu.pk/~eig/precon.html (accessed on 10 February 2025)
39. Pipattanasomporn M. Rahman S. Teklu M. CU-BEMS, Smart Building Electricity Consumption and Indoor Environmental Sensor Datasets Sci. Data 2020 7 241 10.1038/s41597-020-00582-3 32686680
40. Wang K. Cheng L. Wang R. Evolutionary Game-Theoretic Approach to Enhancing User–Grid Cooperation in Peak Shaving: Integrating Whole-Process Democracy (Deliberative Governance) in Renewable Energy Systems Mathematics 2025 13 2463 10.3390/math13152463

Issue

Copyright MDPI