Deep Learning Model for Feature Extraction and Anomaly Recognition in High-Dimensional Energy Metering Data

Huakun Que; Zetao Jiang; Zhifeng Zhou; Yongsheng He; Xin Liu

doi:10.4108/ew.9363

Authors

Huakun Que Guangdong Power Grid Co., Ltd
Zetao Jiang Guangdong Power Grid Co., Ltd
Zhifeng Zhou China Southern Power Grid (China)
Yongsheng He Guangdong Power Grid Co., Ltd
Xin Liu Guangdong Power Grid Co., Ltd

DOI:

https://doi.org/10.4108/ew.9363

Keywords:

energy consumption, deep learning-based approach, high dimensional energy metering data

Abstract

Introduction: The rapid expansion of energy networks has significantly increased energy consumption, resulting in higher electricity costs. Abnormal energy usage in buildings and industries, often caused by system malfunctions, leads to substantial energy waste. Detecting such anomalies is essential for cost control and efficient energy management.

Objectives: This study aims to develop a deep learning-based method to detect anomalies in high-dimensional energy metering data, overcoming the limitations of existing techniques that struggle with data complexity and lack effective contextual analysis.

Methods: High-dimensional metering data from a city energy provider is processed using a Convolutional Autoencoder (CAE) to extract deep features and reduce dimensionality. These features are then fed into a Cascaded Long Short-Term Memory (CLSTM) network, which identifies anomalous patterns in the data.

Results: The cascaded CLSTM model effectively detects anomalies in the energy consumption data by accurately predicting deviations from normal patterns.

Conclusion: The proposed CAE-CLSTM approach enhances anomaly detection in complex energy datasets, enabling more effective monitoring and reducing unnecessary energy waste and costs.

Downloads

Download data is not yet available.

References

[1] Pan, H., Yin, Z., & Jiang, X. (2022). High-dimensional energy consumption anomaly detection: A deep learning-based method for detecting anomalies. Energies, 15, 6139. https://doi.org/10.3390/en15176139 DOI: https://doi.org/10.3390/en15176139

[2] Chiosa, R., SavinoPiscitelli, M., & Capozzoli, A. (2021). A data analytics-based energy information system (EIS) tool to perform meter-level anomaly detection and diagnosis in buildings. Energies, 14, 237. https://doi.org/10.3390/en14010237 DOI: https://doi.org/10.3390/en14010237

[3] Shen, Y., Bo, J., Li, K., Chen, S., Qiao, L., & Li, J. (2019). High-dimensional data anomaly detection framework based on feature extraction of the elastic network. International Conference on Machine Learning and Intelligent Communications. (DOI not found) DOI: https://doi.org/10.1007/978-3-030-32388-2_1

[4] Hopf, K., Sodenkamp, M., Kozlovkiy, I., & Staake, T. (2014). Feature Extraction and Filtering for Household Classification Based on Smart Electricity Meter Data Computer Science - Research and Development. https://doi.org/10.1007/s00450-014-0259-9 DOI: https://doi.org/10.1007/s00450-014-0294-4

[5] Ryu, S., Choi, H., Lee, H., & Kim, H. (2015). Convolutional autoencoder-based feature extraction and clustering for customer load analysis. Journal of Latex Class Files, 14(8). (DOI not found)

[6] Khan, W., Walker, S., & Zeiler, W. (2023). A bottom-up framework for analyzing city-scale energy data using high-dimension reduction techniques. Sustainable Cities and Society, 89, 104323. https://doi.org/10.1016/j.scs.2023.104323 DOI: https://doi.org/10.1016/j.scs.2022.104323

[7] Mohajeri, M., Ghassemi, A., & Gulliver, T. A. (2020). Fast big data analytics for smart meter data. IEEE Open Journal of the Communications Society. https://doi.org/10.1109/OJCOMS.2020.3017727 DOI: https://doi.org/10.1109/OJCOMS.2020.3038590

[8] Qizhen, S., HaoFangzhou, F., Shen, C., Ma, G., Huang, Y., & Wu, Y. (2019). Analysis of users' electricity consumption behaviour in the distribution networks based on high-dimensional random matrices. (pp. 280-288). (DOI not found)

[9] Chahinea, K., Drissia, K. E. K., Pasquiera, C., Kerrouma, K., Faurea, C., Jouannetb, T., & Michou, M. (2011). Electric load disaggregation in smart metering using a novel feature extraction method and supervised classification. Energy Procedia, 6, 627–632. https://doi.org/10.1016/j.egypro.2011.05.120 DOI: https://doi.org/10.1016/j.egypro.2011.05.072

[10] Al-Ghaili, A. M., Ibrahim, Z.-A., Shah Hairi, S., Abdul Rahim, F., Baskaran, H., Mohd Ariffin, N. A., & Kasim, H. (2021). A review of anomaly detection techniques in advanced metering infrastructure. Bulletin of Electrical Engineering and Informatics, 10(1), 266–273. https://doi.org/10.11591/eei.v10i1.2476 DOI: https://doi.org/10.11591/eei.v10i1.2026

[11] Yuan, Y., & Jia, K. (2015). A distributed anomaly detection method of operation energy consumption using smart meter data. International Conference on Information Hiding and Multimedia Processing. (DOI not found) DOI: https://doi.org/10.1109/IIH-MSP.2015.38

[12] Liu, X., Ding, Y., Tang, H., & Xiao, F. (2021). A data mining-based framework for the identification of daily electricity usage patterns and anomaly detection in building electricity consumption data. Energy and Buildings, 231, 110601. https://doi.org/10.1016/j.enbuild.2020.110601 DOI: https://doi.org/10.1016/j.enbuild.2020.110601

[13] Kaymakci, C., Wenninger, S., & Sauer, A. (2021). Energy anomaly detection in industrial applications with long short-term memory-based autoencoders. Procedia CIRP, 104, 182–187. https://doi.org/10.1016/j.procir.2021.11.031 DOI: https://doi.org/10.1016/j.procir.2021.11.031

[14] Hocka, D., Kappesa, M., & Ghitab, B. (2019). Using multiple data sources to detect manipulated electricity meters by an entropy-inspired metric. Sustainable Energy, Grids and Networks, 19, 30188-2. (DOI not found)

[15] Mascali, L., Schiera, D. S., Eiraudo, S., Barbierato, L., Giannantonio, R., Patti, E., Bottaccioli, L., & Lanzini, A. (2023). A machine learning-based anomaly detection framework for building electricity consumption data. Sustainable Energy, Grids and Networks, 36, 101194. https://doi.org/10.1016/j.segan.2023.101194 DOI: https://doi.org/10.1016/j.segan.2023.101194

[16] Xu, C., & Chen, H. (2020). A Hybrid Data Mining Approach for Anomaly Detection and Evaluation in Residential Buildings' Energy Data Energy & Buildings, 215, 109864. https://doi.org/10.1016/j.enbuild.2020.109864 DOI: https://doi.org/10.1016/j.enbuild.2020.109864

[17] Himeur, Y., Alsalemi, A., Bensaali, F., & Amira, A. (2020). A novel approach for detecting anomalous energy consumption based on micro-moments and deep neural networks. Cognitive Computation, 12, 1381–1401. https://doi.org/10.1007/s12559-020-09757-1 DOI: https://doi.org/10.1007/s12559-020-09764-y

[18] Wang, X., Zhao, T., Liu, H., & He, R. (2019). Power consumption predicting and anomaly detection based on long short-term memory neural network. IEEE 4th International Conference on Cloud Computing and Big Data Analytics. https://doi.org/10.1109/ICCCBDA.2019.8725731 DOI: https://doi.org/10.1109/ICCCBDA.2019.8725704

[19] Fan, C., Xiao, F., Zhao, Y., & Wang, J. (2018). Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data. Applied Energy, 211, 1123–1135. https://doi.org/10.1016/j.apenergy.2017.12.080 DOI: https://doi.org/10.1016/j.apenergy.2017.12.005

[20] Granell, R., Axon, C. J., Kolokotroni, M., & Wallom, D. C. H. (2022). A reduced-dimension feature extraction method to represent retail store electricity profiles. Energy & Buildings, 276. https://doi.org/10.1016/j.enbuild.2022.112529 DOI: https://doi.org/10.1016/j.enbuild.2022.112508

[21] Bădic, A., Bădic, C., Bolanowski, M., Fidanova, S., Ganzha, M., Harizanov, S., Ivanovic, M., & Lirkov, I. (2021). Cascaded anomaly detection with coarse sampling in distributed systems. In International Conference on Big Data Analytics (pp. 181-200). Springer. https://doi.org/10.1007/978-3-030-78425-3_12 DOI: https://doi.org/10.1007/978-3-030-96600-3_13

[22] Chen, Z., Freihaut, J., Lin, B., & Wang, C. D. (2018). Inverse energy model development via high-dimensional data analysis and sub-metering priority in building data monitoring. Energy and Buildings, 172, 116-124. https://doi.org/10.1016/j.enbuild.2018.05.031 DOI: https://doi.org/10.1016/j.enbuild.2018.04.061

[23] Pang, G., Shen, C., Cao, L., & Van Den Hengel, A. (2020). Deep learning for anomaly detection: A review. arXiv preprint arXiv:2007.02500. https://arxiv.org/abs/2007.02500

[24] Choi, K., Yi, J., Park, C., & Yoon, S. (2021). Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access. https://doi.org/10.1109/ACCESS.2021.3084052 DOI: https://doi.org/10.1109/ACCESS.2021.3107975

[25] Popa, M. (2011). Data collecting from smart meters in an advanced metering infrastructure. 15th International Conference on Intelligent Engineering Systems. (DOI not found) DOI: https://doi.org/10.1109/INES.2011.5954734

[26] Hua, S., Ma, B., Gao, Y., & Li, X. (2022). Anomaly detection method for metering data of electric energy meter based on association rule. 9th International Forum on Electrical Engineering and Automation (IFEEA), 825-828. https://doi.org/10.1109/IFEEA55194.2022.9827574 DOI: https://doi.org/10.1109/IFEEA57288.2022.10038173

[27] Dai, W., Liu, X., Heller, A., & Nielsen, P. S. (2022). Smart meter data anomaly detection using variational recurrent autoencoders with attention. arXiv preprint. https://arxiv.org/abs/2205.10758 DOI: https://doi.org/10.1007/978-3-031-10525-8_25

[28] Lee, S., Nengroo, S. H., Jin, H., Doh, Y., Lee, C., Heo, T., & Har, D. (2023). Anomaly detection of smart metering system for power management with battery storage system/electric vehicle. ETRI Journal, 45(4), 650-665. https://doi.org/10.4218/etrij.2022-0159 DOI: https://doi.org/10.4218/etrij.2022-0135

[29] Lee, S., Jin, H., Nengroo, S. H., Doh, Y., Lee, C., Heo, T., & Har, D. (2022). Smart metering system capable of anomaly detection by bi-directional LSTM autoencoder. In 2022 IEEE International Conference on Consumer Electronics (ICCE) (pp. 1-6). IEEE. https://doi.org/10.1109/ICCE54181.2022.9721175 DOI: https://doi.org/10.1109/ICCE53296.2022.9730398

[30] Gudivaka, B. R., Almusawi, M., Priyanka, M. S., Dhanda, M. R., & Thanjaivadivel, M. (2024, May). An Improved Variational Autoencoder Generative Adversarial Network with Convolutional Neural Network for Fraud Financial Transaction Detection. In 2024 Second International Conference on Data Science and Information System (ICDSIS) (pp. 1-4). IEEE. DOI: https://doi.org/10.1109/ICDSIS61070.2024.10594271

[31] Basani, D. K. R., Gudivaka, B. R., Gudivaka, R. L., & Gudivaka, R. K. (2024). Enhanced Fault Diagnosis in IoT: Uniting Data Fusion with Deep Multi-Scale Fusion Neural Network. Internet of Things, 101361. DOI: https://doi.org/10.1016/j.iot.2024.101361

[32] Kardi, M., AlSkaif, T., Tekinerdogan, B., & Catalao, J. P. S. (2021). Anomaly detection in electricity consumption data using deep learning. In 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe) (pp. 1-6). IEEE. https://doi.org/10.1109/EEEIC/ICPSEurope51590.2021.9589813 DOI: https://doi.org/10.1109/EEEIC/ICPSEurope51590.2021.9584650

[33] Moon, J.-H., Yu, J.-H., & Sohn, K.-A. (2022). An ensemble approach to anomaly detection using high- and low-variance principal components. Computers and Electrical Engineering, 99, 107773. https://doi.org/10.1016/j.compeleceng.2022.107773 DOI: https://doi.org/10.1016/j.compeleceng.2022.107773

[34] Wang, G. P., & Yang, J. X. (2019). SKICA: A feature extraction algorithm based on supervised ICA with kernel for anomaly detection. Journal of Intelligent & Fuzzy Systems, 36(1), 761-773. https://doi.org/10.3233/JIFS-169269 DOI: https://doi.org/10.3233/JIFS-17749

[35] Rosa, G. H. de, Roder, M., Santos, D. F. S., & Costa, K. A. P. (2021). Enhancing anomaly detection through restricted Boltzmann machine features projection. International Journal of Information Technology, 13, 49-57. https://doi.org/10.1007/s41870-020-00553-2 DOI: https://doi.org/10.1007/s41870-020-00535-4

[36] Valivarthi, D. T., & Hemnath, R. (2018). Cloud-Integrated Wavelet Transform and Particle Swarm Optimization for Automated Medical Anomaly Detection. International Journal of Engineering Research and Science & Technology, 14(1), 17-27.