Statistical Approach with Machine Learning- Based Intrusion Detection System for CyberAttack Discrimination in the Smart Grid
##plugins.themes.academic_pro.article.main##
Abstract
With rapid power grid digitalisation, keeping the private communications network utilities separate from the public communications networks is increasingly more challenging. It paves the way for the attacker to intrude into the industrial control system by compromising the networks. The proposed framework of Statistical Approach with a Machine Learning classifier (SAML) with Synthetic Minority Oversampling Technique (SMOTE) aims to improve early cyberattack discrimination in the smart grid with optimal hyperparameterized tuning of Principal Component Analysis (PCA) with ExtraTrees and AdaBoost Classifier for Feature Extraction (Dimensionality Reduction), bagging, and boosting, respectively. The significance of the SAML-PCA is that it can handle missing rates by replacing INFinity seen attack records with Zero for the specific column of apparent impedance of the relay to avoid blackouts and cascading failures. The proposed SAML-PCA model achieves a higher accuracy of 95.28% for ExtraTrees with Adaboost Classifier than the ML Classifiers and existing approaches.
##plugins.themes.academic_pro.article.details##
How to Cite
Nakkeeran , M., Narayanan, V. A., Sivakumar, P. B., & Balamurugan, S. (2024). Statistical Approach with Machine Learning- Based Intrusion Detection System for CyberAttack Discrimination in the Smart Grid. Power Research - A Journal of CPRI, 20(1), 7–15. https://doi.org/10.33686/pwj.v20i1.1162
References
- Sridhar S, Hahn A, Govindarasu M. Cyber–physical system security for the electric power grid. Proc of the IEEE. 2012; 100(1):210-24. https://doi.org/10.1109/JPROC.2011.2165269 DOI: https://doi.org/10.1109/JPROC.2011.2165269
- Liu CC, Stefanov A, Hong J, Panciatici P. Intruders in the grid. IEEE Pow Energ Mag. 2012; 10(1):58-66. https://doi.org/10.1109/MPE.2011.943114 DOI: https://doi.org/10.1109/MPE.2011.943114
- Amin BMR, Hossain MJ, Anwar A, Zaman S. Cyber attacks and faults discrimination in intelligent electronic devicebased energy management systems. Electron. 2021; 10(6):650. https://doi.org/10.3390/electronics10060650 DOI: https://doi.org/10.3390/electronics10060650
- Hemsley KE, Fisher RE. History of industrial control system cyber incidents. Techn Rep: Hist Indust Cont Syst Cyber Incid. 2018. https://doi.org/10.2172/1505628 DOI: https://doi.org/10.2172/1505628
- Rajkumar VS, Ştefanov A, Presekal A, Pálenský P, Rueda JL. Cyber attacks on power grids: Causes and propagation of cascading failures. IEEE Access. 2023; 11:103154-76. https://doi.org/10.1109/ACCESS.2023.3317695 DOI: https://doi.org/10.1109/ACCESS.2023.3317695
- Recorded Future. Continued targeting of Indian power grid assets by Chinese state-sponsored activity group [Internet]. 2022. [cited 7 Dec 2022]. Available from: https://go.recordedfuture.com/hubfs/reports/ta-20220406.pdf
- Peng C, Sun H, Yang M, Wang YL. A survey on security communication and control for smart grids Under malicious cyber attacks. IEEE Trans Syst, Man, Cybernet: Syst. 2019; 49(8):1554-69. https://doi.org/10.1109/ TSMC.2018.2884952 DOI: https://doi.org/10.1109/TSMC.2018.2884952
- Sahani N, Zhu R, Cho JH, Liu CC. Machine learning-based intrusion detection for smart grid computing: A survey. ACM Transact Cyber-Phy Syst. 2023; 7(2):1-31. https://doi.org/10.1145/3578366 DOI: https://doi.org/10.1145/3578366
- Hink RCB, Beaver JM, Buckner MA, Morris T, Adhikari U, Pan S. Machine learning for power system disturbance and cyber-attack discrimination. 2014 7th Inter Symp Resil Cont Syst; 2014. https://doi.org/10.1109/ISRCS.2014.6900095 DOI: https://doi.org/10.1109/ISRCS.2014.6900095
- Ankitdeshpandey, Karthi R. Development of intrusion detection system using deep learning for classifying attacks in power systems. Adv Intell Syst Comput. 2020:755-66. https://doi.org/10.1007/978-981-15-4032-5_68 DOI: https://doi.org/10.1007/978-981-15-4032-5_68
- Mohan VS, Sankaran S. Intelligent approach for analysis and diagnosis of attack, fault and load Variation in SCADA systems: A power system application. Lect Note Elect Eng. 2022:1-28. https://doi.org/10.1007/978-98116-6081-8_1 DOI: https://doi.org/10.1007/978-981-16-6081-8_1
- Pan S, Morris T, Adhikari U. Classification of disturbances and cyber-attacks in power systems using heterogeneous time-synchronized data. IEEE Transact Ind Inform. 2015; 11(3):650-62. https://doi.org/10.1109/TII.2015.2420951 DOI: https://doi.org/10.1109/TII.2015.2420951
- Adhikari U, et al. Industrial Control System (ICS) cyber attack datasets used in the experimentation. [Internet]; 2014. Available from: http://www.ece.uah.edu/~thm0009/ icsdatasets/triple.7z at website: https://sites.google.com/a/uah.edu/tommy-morris-uah/ics-data-sets Dataset Description: http://www.ece.uah.edu/~thm0009/icsdatasets/ PowerSystem_Dataset_README.pdf
- Balan A, Srujan TL, Manitha PV, Deepa K. Detection and analysis of faults in transformer using machine learning. 2023 Internat Conf Intell Data Comm Technol Internet Things (IDCIoT), India: Bengaluru; 2023. https://doi.org/10.1109/IDCIoT56793.2023.10052786 DOI: https://doi.org/10.1109/IDCIoT56793.2023.10052786
- Nakkeeran M, Narayanan VA. Anomaly detection in SCADA industrial control systems using bi-directional long short-term memory. Lect Note Elect Engineer. 2023; 415-36. https://doi.org/10.1007/978-981-99-3481-2_33 DOI: https://doi.org/10.1007/978-981-99-3481-2_33