Abnormal behaviour recognition technology in smart grid monitoring based on artificial intelligence
-
Liu Xiaowei
,
Liu Ying
Abstract
This paper aims to solve the problem of insufficient accuracy of abnormal behaviour recognition in smart grid monitoring. By applying the CNN (Convolutional Neural Network)- BiLSTM (Bidirectional Long Short-Term Memory) model, combined with spatial feature extraction and time series analysis, the detection ability of complex abnormal patterns is improved. The safety and stability of power grid operation are guaranteed, and efficient management and accurate fault diagnosis of smart grid are realized. Multidimensional time series data, including voltage, current, power factor, and other information, are obtained from sensors and equipment of smart grids, and data cleaning, abnormal annotation, and standardization are performed. The sliding window method is used to divide the time series data to adapt to the input of the deep learning model. The model structure includes a CNN layer for extracting local features, a BiLSTM layer for capturing time series dependencies, and finally a fully connected layer for abnormal behaviour classification. In the test set, the average accuracy of epochs within 30–50 times reaches 97.6 %. Experimental findings demonstrate that the accuracy, precision, and recall of the CNN-BiLSTM model on the test set are better than those of the traditional CNN-LSTM, BiLSTM, and Transformer models. The CNN-BiLSTM model can effectively enhance the accuracy of abnormal behaviour detection in smart grids and provide a reliable solution for the safety monitoring of power grids.
-
Research ethics: The local Institutional Review Board deemed the study exempt from review.
-
Informed consent: Informed consent was obtained from all individuals included in this study, or their legal guardians or wards.
-
Author contributions: All authors are contributed to the design and methodology of this study, the assessment of the outcomes and the writing of the manuscript.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: No funds, grants were received by any of the authors.
-
Data availability: Not applicable.
References
1. Alhamrouni, I, Abdul Kahar, NH, Salem, M, Swadi, M, Zahroui, Y, Kadhim, DJ, et al.. A comprehensive review on the role of artificial intelligence in power system stability, control, and protection: insights and future directions. Appl Sci 2024;14:6214. https://doi.org/10.3390/app14146214.Search in Google Scholar
2. Tiwari, S, Kumar, A. Advances and bibliographic analysis of particle swarm optimization applications in electrical power system: concepts and variants. Evol Intell 2023;16:23–47. https://doi.org/10.1007/s12065-023-00544-4.Search in Google Scholar
3. Xie, X, Li, J, Li, F, Xu, Y, Liu, L, Chen, J, et al.. Intelligent terminal backdoor detection method for new power system. Electr Power Construct 2024;45:45–55. https://doi.org/10.13203/j.epc.2024.01045.Search in Google Scholar
4. Zhang, Y, Lu, D, Qiu, X, Li, F. Ship classification of small sample SAR images based on scattering point topology and dual-branch convolutional neural network. J Radars 2023;13:411–27. https://doi.org/10.1109/JR.2023.1001623.Search in Google Scholar
5. Wu, F, Wang, W, Liu, W. X-ray weld defect detection based on attention mechanism and convolutional neural network. Sci Technol Eng 2023;23:3387–95. https://doi.org/10.3923/jstae.2023.3387-3395.Search in Google Scholar
6. He, R, Liang, H, Wu, J, Xie, H, Shahidehpour, M. Reliability assessment of cyber-physical distribution system using multi-dimensional information network model. IEEE Trans Smart Grid 2023;14:4683–92. https://doi.org/10.1109/TSG.2023.3180294.Search in Google Scholar
7. Peng, H, Li, S, Shangguan, L, Fan, Y, Zhang, H. Analysis of wind turbine equipment failure and intelligent operation and maintenance research. Sustainability 2023;15:8333. https://doi.org/10.3390/su15108333.Search in Google Scholar
8. Rangarajan, SS, Raman, R, Singh, A, Shiva, CK, Kumar, R, Sadhu, PK, et al.. DC microgrids: a propitious smart grid paradigm for smart cities. Smart Cities 2023;6:1690–718. https://doi.org/10.3390/smartcities60401690.Search in Google Scholar
9. Bhadani, U. Pillars of power system and security of smart grid. Int J Innovat Res Sci Eng Technol 2024;13:10–15680. https://doi.org/10.15680/IJIRSET.2024.13888.Search in Google Scholar
10. Ahmed, QI, Attar, H, Amer, A, Deif, MA, Solyman, AA. Development of a hybrid support vector machine with grey wolf optimization algorithm for detection of the solar power plants anomalies. Systems 2023;11:237. https://doi.org/10.3390/systems11050237.Search in Google Scholar
11. Harshini, C, Deepthi, G, Reddy, GA, Laxmi, G, Vijaya, G, Rajasree, G. Electricity theft detection in power grids with deep learning and random forests. Int J Manag Res Rev 2023;13:1–10. https://doi.org/10.2139/ssrn.3945967.Search in Google Scholar
12. Varma, R, Kumar, G. Automatic fault detection in industrial smart grids using KNN and ensemble classifiers. El-Cezeri 2023;10:240–52. https://doi.org/10.1016/j.ejcse.2023.02.007.Search in Google Scholar
13. Gunduz, MZ, Das, R. Smart grid security: an effective hybrid CNN-based approach for detecting energy theft using consumption patterns. Sensors 2024;24:1148. https://doi.org/10.3390/s24041148.Search in Google Scholar PubMed PubMed Central
14. Amellal, A, Amellal, I, Seghiouer, H, Ech-Charrat, MR. Improving lead time forecasting and anomaly detection for automotive spare parts with a combined CNN-LSTM approach. Oper Supply Chain Manag Int J 2023;16:265–78. https://doi.org/10.31387/oscm0400226.Search in Google Scholar
15. Yu, X, Zeng, B, Wang, L. Anomaly detection for industrial time series data based on correlation analysis and CNN-BiLSTM with self-attention. Asian J Math Comput Res 2024;31:96–108. https://doi.org/10.35740/ajmcr.v31i2.096-108.Search in Google Scholar
16. Alagarsundaram, P, Ramamoorthy, SK, Mazumder, D, Malathy, V, Soni, M. A short-term load forecasting model using restricted Boltzmann machines and bi-directional gated recurrent unit. In: Proceedings of the 2024 Second International Conference on Networks, Multimedia and Information Technology. IEEE, Bengaluru, India; 2024:1–5 pp.10.1109/NMITCON62075.2024.10699152Search in Google Scholar
17. Devarajan, MV, Aluvala, S, Armoogum, V, Sureshkumar, S, Manohara, HT. Intrusion detection in industrial internet of things based on recurrent rule-based feature selection. In: Proceedings of the 2024 Second International Conference on Networks, Multimedia and Information Technology. IEEE, Bengaluru, India; 2024:1–4 pp.10.1109/NMITCON62075.2024.10698962Search in Google Scholar
18. Basani, DKR, Gudivaka, BR, Gudivaka, RL, Gudivaka, RK. Enhanced Fault diagnosis in IoT: uniting data fusion with deep multi-scale fusion neural network. Internet Things 2024:101361. https://doi.org/10.1016/j.iot.2024.101361.Search in Google Scholar
19. Dhaka, P, Nagpal, B. WoM-based deep BiLSTM: smart disease prediction model using WoM-based deep BiLSTM classifier. Multimed Tool Appl 2023;82:25061–82. https://doi.org/10.1007/s11042-023-15257-0.Search in Google Scholar
20. Kavianpour, P, Kavianpour, M, Jahani, E, Ramezani, A. A CNN-BiLSTM model with attention mechanism for earthquake prediction. J Supercomput 2023;79:19194–226. https://doi.org/10.1007/s11227-023-05009-3.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
