Distribution System Security Protection Model based on OCSVM Combined with DPoS
DOI:
https://doi.org/10.13052/dgaej2156-3306.4157Keywords:
Support vector machine, DPoS algorithm, power distribution system, microgrid, intrusion detection, security protectionAbstract
With the rapid development of information technology in the power field, information security threats have gradually penetrated into the power system. To solve the low efficiency and insufficient accuracy of intrusion detection in multi-microgrid power distribution systems, this study constructs an intrusion detection method for distributed power grids based on One Class Support Vector Machine (OCSVM). Meanwhile, blockchain technology and the Delegated Proof of Stake (DPoS) are combined to build a collaborative detection model. In the collaborative security protection model, the study uses the triggering and polling mechanism to generate proposals, and optimizes the judgment conditions of the DPoS algorithm to improve the applicability to power distribution systems. The attack detection rate of the improved OCSVM model proposed in the study was 4.55% higher than that of the traditional Support Vector Machine (SVM). For model training efficiency, the OCSVM was 6.1 minutes faster than that of the SVM. In the test sample data, the highest accuracy of the OCSVM-DPoS model was 0.989, and the average accuracy was as high as 0.933. In addition, the OCSVM-DPoS model had an average detection rate of 93.46% for tampering attacks and 93.50% for replay attacks, which were also higher than those of other models. The proposed method has high performance in intrusion detection of multi-microgrid distribution systems and has good application prospects in the power grid security management.
Downloads
References
Q. Lu, K. An, J. Li, J. Wang, ‘Network intrusion detection for modern smart grids based on adaptive online incremental learning’, IEEE Trans. Smart Grid, vol. 16, no. 3, pp. 2541–2553, Feb., 2025.
Z. S. Khalafi, M. Dehghani, A. Khalili, A. Sami, N. Vafamand, T. Dragičević, ‘Intrusion detection, measurement correction, and attack localization of PMU networks’, IEEE Trans. Ind. Electron., vol. 69, no. 5, pp. 4697–4706, May, 2022.
M. Xiao, Q. Zhou, Z. Zhang, J. Yin, ‘Real-time intrusion detection in power grids using deep learning: Ensuring dpu data security’, HighTech Innov. J., vol. 5, no. 3, pp. 814–827, Sep., 2024.
O. A. Agboola, J. C. Ogeawuchi, O. E. Akpe, A. A. Abayomi, ‘A conceptual model for integrating cybersecurity and intrusion detection architecture into grid modernization initiatives’, Int. J. Multidiscip. Res. Grow. Eval., vol. 3, no. 1, pp. 1099–1105, Jan., 2022.
S. Bi, J. Wang, J. Song, P. Li, L. Li, ‘Research on the intrusion detection model for power internet of things combining deep belief network and BiLSTM’, J. Cyber Secur. Mobility, vol. 14, no. 3, pp. 653–672, May., 2025.
A. Aljohani, M. AlMuhaini, H. V. Poor, H. M. Binqadhi, ‘A deep learning-based cyber intrusion detection and mitigation system for smart grids’, IEEE Trans. Artif. Intell., vol. 5, no. 8, pp. 3902–3914, Jan., 2024.
D. Upadhyay, J. Manero, M. Zaman, S. Sampalli, ‘Gradient boosting feature selection with machine learning classifiers for intrusion detection on power grids’, IEEE Trans. Netw. Serv. Manage., vol. 18, no. 1, pp. 1104–1116, Oct., 2021.
J. Azimjonov, T. Kim, ‘A comprehensive empirical analysis of data sets, regression-based feature selectors, and linear svm classifiers for intrusion detection systems’, IEEE Int. Things J., vol. 11, no. 12, pp. 34676–34693, Jun., 2024.
S. Amaran, R. M. Mohan, R. Jebakumar, ‘Optimal machine learning based intrusion detection system in wireless sensor networks for surveillance applications’, J. Mob. Multimed., vol. 19, no. 2, pp. 437–450, Mar., 2023.
T. DasT, R. M. Shukla, S. Sengupta, ‘Poisoning the well: Adversarial poisoning on ML-based software-defined network intrusion detection systems’, IEEE Trans. Netw. Sci. Eng., vol. 12, no. 1, pp. 252–262, Nov., 2025.
Z. Serat, S. A. Z. Fatemi, S. Shirzad, ‘Design and economic analysis of on-grid solar rooftop PV system using PVsyst software’, Arch. Advan. Eng. Sci., vol. 1, no. 1, pp. 63–76, Mar., 2023.
C. C. Sun, D. J. Sebastian Cardenas, A. Hahn, C. C. Liu, ‘Intrusion detection for Cybersecurity of smart meters’, IEEE Trans. Smart Grid, vol. 12, no. 1, pp. 612–622, Jul., 2021.
D. Upadhyay, J. Manero, M. Zaman, S. Sampalli, ‘Intrusion detection in SCADA based power grids: Recursive feature elimination model with majority vote ensemble algorithm’, IEEE Trans. Netw. Sci. Eng., vol. 8, no. 3, pp. 2559–2574, Jul., 2021.
A. Presekal, A. Ştefanov, I. Semertzis, P. Palensky, ‘Spatio-temporal advanced persistent threat detection and correlation for cyber-physical power systems using enhanced GC-LSTM’, IEEE Trans. Smart Grid, vol. 16, no. 2, pp. 1654–1666, Oct., 2025.
W, Wang, X, Du, D, Shan, R, Qin, N. Wang, ‘Cloud intrusion detection method based on stacked contractive auto-encoder and support vector machine’, IEEE Trans. Cloud Comput., vol. 10, no. 3, pp. 1634–1646, Jun., 2022.
Z, Lv, J. Wan, ‘Intrusion detection in wireless sensor networks based on IPSO-SVM algorithm’, J. Cyber Secur. Mob., vol. 13, no. 4, pp. 803–822, Jul., 2024.
P. He, Z. Zhu, X. Wang, C. Zhang, W. Yuan, and J. Hao, ‘Research on Supervision System of Power Safety Tools and Equipment Based on Internet of Things Technology’, DGAEJ, vol. 38, no. 04, pp. 1223–1254, May 2023.
G. Abdelmoumin, D. B. Rawat, A. Rahman, ‘On the performance of machine learning models for anomaly-based intelligent intrusion detection systems for the internet of things’, IEEE Int. Things J., vol. 9, no. 6, pp. 4280–4290, Aug., 2022.
N. Sahani, R. Zhu, J. H. Cho, C. C. Liu, ‘Machine learning-based intrusion detection for smart grid computing: A survey’, ACM Trans. Cyber-Phys. Syst., vol. 7, no. 2, pp. 1–31, Apr., 2023.
N. N. Reddy, R. Velpula, P. Raja, and S. Moorthi, ‘Protection Algorithm for Fault Identification and Isolation in DC Microgrid’, DGAEJ, vol. 38, no. 02, pp. 691–714, Jan. 2023.
