Dhanda Supriya, Anne Venkata Praveen Krishna | International Journal of Electrical Power System and Technology | Vol 12, Issue 02
Abstract
In the realm of cybersecurity, the intersection of technology and security measures has spurred significant advancements, particularly in safeguarding electrical systems against cyber threats. This research delves into the evolving landscape of cybersecurity within electrical systems, leveraging machine learning techniques to mitigate challenges. By incorporating cybersecurity protocols with machine learning algorithms, this study demonstrates enhanced security measures tailored for electrical infrastructures, pivotal in ensuring efficiency and resilience. Through meticulous examination, various machine learning models were scrutinized for their efficacy in fortifying security, utilizing diverse datasets pertinent to system vulnerabilities. The findings reveal compelling insights, showcasing the effectiveness of machine learning algorithms in bolstering security measures. Notably, the comparative analysis highlights the prowess of Random Forest with an accuracy of 99.89% in detecting a myriad of attacks with exceptional accuracy, outperforming its counterparts such as Decision Tree and KNN. Additionally, it's observed that while Random Forest achieved superior accuracy, Decision Tree and KNN struggled to recognize specific attack types like multihop, snmpgetattack, and spy attacks. This research underscores the imperative synergy between cybersecurity frameworks and machine learning methodologies, illuminating pathways for fortifying smart electrical systems against cyber threats while ensuring reliable, scalable, adaptive, and real- time protection against evolving cyberattack scenarios and vulnerabilities.
Keywords - Machine Learning, Cyber Security, Electrical Systems, Random Forest, KNN, Decision Tree, Cyber threats.
🔒 This is a subscription article
Full text is available to subscribers and institutional members. Please choose an option below to access it.
SubscribePurchase this articleInstitutional / Login accessReferences
- Newaz AI, Sikder AK, Babun L, Uluagac AS. Heka: A novel intrusion detection system for attacks to personal medical devices. In2020 IEEE Conference on Communications and Network Security (CNS) 2020 Jun 29 (pp. 1-9). IEEE.
- Costilla-Enriquez N, Weng Y. Attack power system state estimation by implicitly learning the underlying models. IEEE Transactions on Smart Grid. 2022 Aug 10;14(1):649-62.
- Kim Y, Hakak S, Ghorbani A. Smart grid security: Attacks and defence techniques. IET Smart Grid. 2023 Apr;6(2):103-23.
- Ibrahim MS, Dong W, Yang Q. Machine learning driven smart electric power systems: Current trends and new perspectives. Applied Energy. 2020 Aug 15;272:115237.
- Yohanandhan RV, Elavarasan RM, Manoharan P, Mihet-Popa L. Cyber-physical power system (CPPS): A review on modeling, simulation, and analysis with cyber security applications. IEEe Access. 2020 Aug 14;8:151019-64.
- Ye J, Giani A, Elasser A, Mazumder SK, Farnell C, Mantooth HA, Kim T, Liu J, Chen B, Seo GS, Song W. A review of cyber–physical security for photovoltaic systems. IEEE Journal of Emerging and Selected Topics in Power Electronics. 2021 Sep 10;10(4):4879-901.
- Ahmed S, Lee Y, Hyun SH, Koo I. Unsupervised machine learning-based detection of covert data integrity assault in smart grid networks utilizing isolation forest. IEEE Transactions on Information Forensics and Security. 2019 Mar 5;14(10):2765-77.
- Ahmed S, Lee Y, Hyun SH, Koo I. Feature selection–based detection of covert cyber deception assaults in smart grid communications networks using machine learning. IEEE Access. 2018 May 11;6:27518-29.
- Wang C, Tindemans S, Pan K, Palensky P. Detection of false data injection attacks using the autoencoder approach. In2020 international conference on probabilistic methods applied to power systems (PMAPS) 2020 Aug 18 (pp. 1-6). IEEE.
- Kotsiopoulos T, Sarigiannidis P, Ioannidis D, Tzovaras D. Machine learning and deep learning in smart manufacturing: The smart grid paradigm. Computer Science Review. 2021 May 1;40:100341.
- Sakhnini J, Karimipour H, Dehghantanha A. Smart grid cyber attacks detection using supervised learning and heuristic feature selection. In2019 IEEE 7th international conference on smart energy grid engineering (SEGE) 2019 Aug 12 (pp. 108-112). IEEE.
- Alkahtani H, Aldhyani TH. Developing cybersecurity systems based on machine learning and deep learning algorithms for protecting food security systems: industrial control systems. Electronics. 2022 May 27;11(11):1717.
- Gao X, Shan C, Hu C, Niu Z, Liu Z. An adaptive ensemble machine learning model for intrusion detection. Ieee Access. 2019 Jun 19;7:82512-21.
- Ustun TS, Hussain SS, Ulutas A, Onen A, Roomi MM, Mashima D. Machine learning-based intrusion detection for achieving cybersecurity in smart grids using IEC 61850 GOOSE messages. Symmetry. 2021 May 8;13(5):826.
- Mazhar T, Irfan HM, Khan S, Haq I, Ullah I, Iqbal M, Hamam H. Analysis of cyber security attacks and its solutions for the smart grid using machine learning and blockchain methods. Future Internet. 2023 Feb 19;15(2):83.
- Ahmed S, Lee Y, Hyun SH, Koo I. Feature selection–based detection of covert cyber deception assaults in smart grid communications networks using machine learning. IEEE Access. 2018 May 11;6:27518-29.
How to cite this article
@article{SupriyaD2026,
author = {Dhanda Supriya and Anne Venkata Praveen Krishna},
title = {Securing Smart Electrical Systems through Comparative Analysis of Machine Learning Models for Classification},
journal = {International Journal of Electrical Power System and Technology},
year = {2026},
volume = {12},
number = {02},
url = {https://journalspub.com/publication/ijepst/article=26884}
}