Abstract
The smart grid has achieved digitalization and interconnection of power systems through the integration of the Internet of Things (IoT), communication networks, and automation technologies. However, these advancements have also made the smart grid a prime target for cyberattacks. To ensure stable operation and protect user privacy, this study integrates long short-term memory (LSTM) networks, the K-means clustering algorithm, and federated learning to design a behavior anomaly detection method. The proposed method effectively safeguards the privacy and security of the smart grid against physical attacks, thereby ensuring its stable operation. Experimental results demonstrate that the fusion algorithm achieves a feature extraction accuracy of 98.7%, while the anomaly detection error rate remains as low as 2.3%. Furthermore, under attack scenarios, the method reduces the risk of privacy leakage by 92.1% and successfully resists over 90% of physical attacks. These findings indicate that the proposed detection method can not only accurately monitor abnormal behaviors in the smart grid but also provide robust protection for grid security in the event of an attack.
References
Takiddin A, Ismail M, Atat R, Davis KR, Serpedin E. Robust graph autoencoder-based detection of false data injection attacks against data poisoning in smart grids. IEEE Transactions on Artificial Intelligence. 2023, 5(3): 1287–1301. DOI: 10.1109/TAI.2023.3286831.
Wu L, Fu S, Luo Y, Yan H, Shi H, Xu M. A robust and lightweight privacy-preserving data aggregation scheme for smart grid. IEEE Transactions on Dependable and Secure Computing. 2023, 21(1): 270–283. DOI: 10.1109/TDSC.2023.3252593.
Vahidi S, Ghafouri M, Au M, Kassouf M, Mohammadi A, Debbabi M. Security of wide-area monitoring, protection, and control (WAMPAC) systems of the smart grid: A survey on challenges and opportunities. IEEE Communications Surveys & Tutorials. 2023, 25(2): 1294–1335. DOI: 10.1109/COMST.2023.3251899.
An D, Zhang F, Cui F, Yang Q. Toward data integrity attacks against distributed dynamic state estimation in smart grid. IEEE Transactions on Automation Science and Engineering. 2023 Jan 17; 21(1): 881–194. DOI: 10.1109/TASE.2023.3236102
Jithish J, Alangot B, Mahalingam N, Yeo KS. Distributed anomaly detection in smart grids: a federated learning-based approach. IEEE Access. 2023, 11(6): 7157–7179. DOI: 10.1109/ACCESS.2023.3237554.
Wang Z, Jiang W, Xu J, Xu Z, Zhou A, Xu M. Grid2Vec: learning node representations of digital power systems for anomaly detection. IEEE Transactions on Smart Grid. 2024, 15(5): 5031–5042. DOI: 10.1109/TSG.2024.3377223.
Guha D, Chatterjee R, Sikdar B. Anomaly detection using lstm-based variational autoencoder in unsupervised data in power grid. IEEE Systems Journal. 2023, 17(3): 4313–4323. DOI:10.1109/jsyst.2023.3266554.
Takiddin A, Atat R, Ismail M, Boyaci O, Davis KR, Serpedin E. Generalized graph neural network-based detection of false data injection attacks in smart grids. IEEE Transactions on Emerging Topics in Computational Intelligence. 2023, 7(3): 618–630. DOI: 10.1109/TETCI.2022.3232821.
Hu P, Gao W, Li Y, Guo X, Hua F, Qiao L. Anomaly detection and state correction in smart grid using EKF and data compensation techniques. IEEE Sensors Journal. 2024, 24(8): 12995–13009. DOI: 10.1109/JSEN.2024.3372973.
Fu M, Shi Y, Zhou Y. Federated learning via unmanned aerial vehicle. IEEE Transactions on Wireless Communications. 2023, 23(4): 2884–2900. DOI: 10.1109/TWC.2023.3303492.
Rykov A, De Amorim RC, Makarenkov V, Mirkin B. Inertia-based indices to determine the number of clusters in K-Means: an experimental evaluation. IEEE Access. 2024, 12(5): 11761–11773. DOI: 10.1109/ACCESS.2024.3350791.
Helmy I, Tarafder P, Choi W. LSTM-GRU model-based channel prediction for one-bit massive MIMO system. IEEE Transactions on Vehicular Technology. 2023, 72(8): 11053–11057. DOI: 10.1109/TVT.2023.3262951.
Zhou X, Liang W, Kevin I, Wang K, Yan Z, Yang L T, Jin Q. Decentralized P2P federated learning for privacy-preserving and resilient mobile robotic systems. IEEE Wireless Communications. 2023, 30(2): 82–89. DOI: 10.1109/MWC.004.2200381.
Liu H, Chen J, Dy J, Fu Y. Transforming complex problems into K-means solutions. IEEE transactions on pattern analysis and machine intelligence. 2023, 45(7): 9149–9168. DOI: 10.1109/TPAMI.2023.3237667.
Zhang X, Chau TK, Chow YH, Fernando T, Iu HH. A novel sequence to sequence data modelling based CNN-LSTM algorithm for three years ahead monthly peak load forecasting. IEEE Transactions on Power Systems. 2023, 39(1): 1932–1947. DOI: 10.1109/TPWRS.2023.3271325.
Yu P, Huang W, Zhang R, Qian X, Li H, Chen H. GuardGrid: A Queriable and Privacy-Preserving Aggregation Scheme for Smart Grid via Function Encryption. IEEE Internet of Things Journal. 2025, 12(11): 17622–17633. DOI: 10.1109/JIOT.2025.3539724.
Sarieddine K, Sayed MA, Jafarigiv D, Atallah R, Debbabi M, Assi C. A real-time cosimulation testbed for electric vehicle charging and smart grid security. IEEE Security & Privacy. 2023, 21(4): 74–83. DOI: 10.1109/MSEC.2023.3247374.
Liu Y, Kang Y, Zou T, Pu Y, He Y, Ye X, Ouyang Y, Zhang YQ, Yang Q. Vertical federated learning: Concepts, advances, and challenges. IEEE Transactions on Knowledge and Data Engineering. 2024, 36(7): 3615–3634. DOI: 10.1109/TKDE.2024.3352628.
Abdi N, Albaseer A, Abdallah M. The role of deep learning in advancing proactive cybersecurity measures for smart grid networks: A survey. IEEE Internet of Things Journal. 2024, 11(9): 16398–16421. DOI: 10.1109/JIOT.2024.3354045.
Fan Y, Liu J, Ye H, Lyu Z. TA-LSTM: a time and attribute aware LSTM for deep flight track clustering. IEEE Transactions on Aerospace and Electronic Systems. 2023, 59(5): 7047–7060. DOI: 10.1109/TAES.2023.3285203.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Journal of Cyber Security and Mobility