تشخیص نفوذ تزریق داده جعلی در شبکه های هوشمند قدرت: رویکرد مبتنی بر تلفیق روش های یادگیری ماشین
محمدرضا پورشیرازی
1
(
دانشکده مهندسی برق، دانشگاه ازاد اسلامی واحد مرودشت، فارس، ایران
)
محسن سیماب
2
(
دانشکده مهندسی برق، دانشگاه آزاد اسلامی واحد مرودشت، فارس، ایران
)
سیدعلیرضا میرزایی
3
(
دانشکده مهندسی برق، دانشگاه آزاد اسلامی واحد داریون، شیراز، ایران
)
بهادر فانی
4
(
دانشکده مهندسي برق- واحد اصفهان (خوراسگان)، دانشگاه آزاد اسلامی، اصفهان، ايران
)
کلید واژه: شبکه های هوشمند, سیستم های قدرت, الگوریتم های هوشمند, تزریق داده جعلی, تلفیق داده, تشخیص نفوذ, یادگیری ماشین,
چکیده مقاله :
در این مقاله، یک رویکرد جدید برای تشخیص نفوذ تزریق داده های جعلی (FDI) ارائه شده است که از تلفیق چهار روش یادگیری ماشین پایه شامل جنگل تصادفی (RF)، ماشین ارتقای گرادیان (GBM)، آنالیز تشخیصی خطی (LDA) و رگرسیون لجستیک (LR) بهره می‌برد. خروجی‌های این روش‌ها بر اساس الگوریتمی هوشمند مبتنی بر شبکه عصبی-فازی تطبیقی (ANFIS) با یکدیگر تلفیق می‌شوند تا به دقت و کارایی بالاتری در تشخیص FDI دست یابیم. پس از استخراج و کاهش تعداد ویژگی های تمایزبخش مستخرج از واحدهای اندازه گیری فازور (PMU)، با بهره گیری از تکنیک کاهش ابعاد جنگل تصادفی، بردارهای حالت بهینه، انتخاب و برچسب گذاری شده تا در مرحله آموزش و آزمایش طبقه بندی کننده های پایه، مورد استفاده قرار گیرد. در ادامه، پس از آموزش انفرادی الگوریتم‌های پایه و بهینه سازی ابرپارامترها، خروجی پیش بینی هر مدل، جهت تشخیص وضعیت‌های دارای اخلال، تعیین می‌گردد. با تلفیق هوشمند خروجی های مدل های پایه، توسط الگوریتمی مبتنی بر ANFIS، امکان تشخیص نمونه های نرمال از ناهنجار، با دقت بالا و حساسیت کم به دامنه نفوذهای FDI فراهم گردیده است. روش پیشنهادی بر روی سیستم قدرت IEEE 14 باسه مورد بررسی قرار گرفته است. نتایج به دست آمده نشان می‌دهد که رویکرد تلفیقی پیشنهادی نسبت به روش‌های پایه موجود، عملکردی بهتر در تشخیص نفوذهای FDI دارد. این رویکرد به طور قابل توجهی، نرخ خطای مثبت کاذب و نرخ تشخیص (DR) را بهبود می‌دهد که کاربرد آن را به عنوان ابزاری مؤثر برای ارتقای امنیت شبکه‌های هوشمند در برابر نفوذهای FDI نشان می دهد.
چکیده انگلیسی :
In this paper, a novel approach is proposed for False Data Injection (FDI) intrusion detection in smart power grids, which utilizes the fusion of four machine learning base methods including Random Forest (RF), Gradient Boosting Machine (GBM), Linear Discriminant Analysis (LDA), and Logistic Regression (LR). The outputs of these methods are integrated using an intelligent algorithm based on Adaptive Neuro-Fuzzy Inference System (ANFIS) to achieve higher accuracy and efficiency in detecting these types of intrusions. After extracting and reducing the number of discriminative features extracted from Phasor Measurement Units (PMUs), using the Random Forest dimensionality reduction technique, the optimal state vectors are selected and labeled for use in the training and testing phase of the base classifiers. Then, after individual training of the base algorithms and hyperparameter optimization, the base models are applied to the test vector, and the predicted output of each model is determined to detect anomalous conditions. By intelligently integrating the outputs of the base models using an ANFIS-based algorithm, it is possible to distinguish normal samples from anomalies with high accuracy and low sensitivity to noise and uncertainty in the measurement data. The proposed method was evaluated on the IEEE 14-bus power system. The simulation results show that the proposed fusion approach outperforms the existing baseline methods in FDI detection. This approach significantly reduces the False Positive Rate (FPR) and increases the Detection Rate (DR), which demonstrates its application as an effective tool for enhancing the security of smart grids against FDI intrusions.
[1] Q. Wang, W. Tai, Y. Tang, and M. Ni, "Review of the false data injection attack against the cyber‐physical power system," IET Cyber‐Physical Systems: Theory & Applications, vol. 4, no. 2, pp. 101-107, 2019.
[2] D. Liu, X. Zhang, and K. T. Chi, "A tutorial on modeling and analysis of cascading failure in future power grids," IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 1, pp. 49-55, 2020.
[3] M. Zhang et al., "False data injection attacks against smart gird state estimation: Construction, detection and defense," Science China Technological Sciences, vol. 62, no. 12, pp. 2077-2087, 2019.
[4] آف, سیماب, نفر, میرزایی, and سیدعلیرضا, "تنظیم فرکانس در ریزشبکه های ترکیبی جزیره ای در حضور عدم قطعیت ها مبتنی برکنترل کننده های عصبی-فازی تطبیقی," مهندسی مخابرات جنوب, vol. 12, no. 48, pp. 51-70, 2023.
[5] R. Deng, G. Xiao, and R. Lu, "Defending against false data injection attacks on power system state estimation," IEEE Transactions on Industrial Informatics, vol. 13, no. 1, pp. 198-207, 2015.
[6] M. A. Husnoo, A. Anwar, N. Hosseinzadeh, S. N. Islam, A. N. Mahmood, and R. Doss, "False data injection threats in active distribution systems: A comprehensive survey," Future Generation Computer Systems, vol. 140, pp. 344-364, 2023.
[7] D. Ding, Q.-L. Han, X. Ge, and J. Wang, "Secure state estimation and control of cyber-physical systems: A survey," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 51, no. 1, pp. 176-190, 2020.
[8] Y. Liu, P. Ning, and M. K. Reiter, "False data injection attacks against state estimation in electric power grids," ACM Transactions on Information and System Security (TISSEC), vol. 14, no. 1, pp. 1-33, 2011.
[9] M. Mohammadpourfard, A. Sami, and A. R. Seifi, "A statistical unsupervised method against false data injection attacks: A visualization-based approach," Expert Systems with Applications, vol. 84, pp. 242-261, 2017.
[10] Q. Liu, V. Hagenmeyer, and H. B. Keller, "A review of rule learning-based intrusion detection systems and their prospects in smart grids," IEEE Access, vol. 9, pp. 57542-57564, 2021.
[11] J. Cao et al., "A novel false data injection attack detection model of the cyber-physical power system," IEEE Access, vol. 8, pp. 95109-95125, 2020.
[12] M. Wazid, A. K. Das, V. Chamola, and Y. Park, "Uniting cyber security and machine learning: Advantages, challenges and future research," ICT Express, vol. 8, no. 3, pp. 313-321, 2022.
[13] O. A. Alimi, K. Ouahada, and A. M. Abu-Mahfouz, "A review of machine learning approaches to power system security and stability," IEEE Access, vol. 8, pp. 113512-113531, 2020
. [14] R. Nawaz, R. Akhtar, M. A. Shahid, I. M. Qureshi, and M. H.
130, p. 106819, 2021.
[15] K. Pedramnia and S. Shojaei, "Detection of false data injection attack in smart grid using decomposed nearest neighbor techniques," in 2020 10th Smart Grid Conference (SGC), 2020, pp. 1-6: IEEE.
[16] D. Hu, S. Wu, J. Wang, and D. Shi, "Training A Dynamic Neural Network to Detect False Data Injection Attacks Under Multiple Unforeseen Operating Conditions," IEEE Transactions on Smart Grid, 2023.
[17] M. Ahmadzadeh, A. Abazari, M. Ghafouri, A. Ameli, and S. Muyeen, "A Deep Convolutional Neural Network-based Approach to Detect False Data Injection Attacks on PV-Integrated Distribution Systems," IEEE Access, 2024.
[18] P. Hu, W. Gao, Y. Li, M. Wu, F. Hua, and L. Qiao, "Detection of False Data Injection Attacks in Smart Grids Based on Expectation Maximization," Sensors, vol. 23, no. 3, p. 1683, 2023.
[19] M. Ashrafuzzaman, S. Das, Y. Chakhchoukh, S. Duraibi, S. Shiva, and F. T. Sheldon, "Supervised Learning for Detecting Stealthy False Data Injection Attacks in the Smart Grid," in Advances in Security, Networks, and Internet of Things: Proceedings from SAM'20, ICWN'20, ICOMP'20, and ESCS'20, 2021, pp. 291-305: Springer.
[20] T. Berghout, M. Benbouzid, and S. Muyeen, "Machine learning for cybersecurity in smart grids: A comprehensive review-based study on methods, solutions, and prospects," International Journal of Critical Infrastructure Protection, p. 100547, 2022.
[21] A. Kumar, N. Saxena, S. Jung, and B. J. Choi, "Improving detection of false data injection attacks using machine learning with feature selection and oversampling," Energies, vol. 15, no. 1, p. 212, 2021.
[22] B. Li, R. Lu, G. Xiao, T. Li, and K.-K. R. Choo, "Detection of false data injection attacks on smart grids: A resilience-enhanced scheme," IEEE Transactions on Power Systems, vol. 37, no. 4, pp. 2679-2692, 2021.
[23] A. Ayad, H. E. Farag, A. Youssef, and E. F. El-Saadany, "Detection of false data injection attacks in smart grids using recurrent neural networks," in 2018 IEEE power & energy society innovative smart grid technologies conference (ISGT), 2018, pp. 1-5: IEEE.
[24] M. Ashrafuzzaman, S. Das, Y. Chakhchoukh, S. Shiva, and F. T. Sheldon, "Detecting stealthy false data injection attacks in the smart grid using ensemble-based machine learning," Computers & Security, vol. 97, p. 101994, 2020.
[25] S. Almasabi et al., "A Novel Technique to Detect False Data Injection Attacks on Phasor Measurement Units," Sensors, vol. 21, no. 17, p. 5791, 2021.
[26] S. Y. Derakhshandeh and R. Pourbagher, "Robust coupled single-port method based on PMU-based state estimation method for voltage stability assessment," International Journal of Electrical Power & Energy Systems, vol. 151, p. 109150, 2023.
[27] P. H. Foo and G. W. Ng, "High-level information fusion: An overview," J. Adv. Inf. Fusion, vol. 8, no. 1, pp. 33-72, 2013.
[28] G. Biau and E. Scornet, "A random forest guided tour," Test, vol. 25, pp. 197-227, 2016.
[29] A. Natekin and A. Knoll, "Gradient boosting machines, a tutorial," Frontiers in neurorobotics, vol. 7, p. 21, 2013.
[30] A. Tharwat, "Linear vs. quadratic discriminant analysis classifier: a tutorial," International Journal of Applied Pattern Recognition, vol. 3, no. 2, pp. 145-180, 2016.
[31] S. Deng, M. Wei, M. Xu, and W. Cai, "Prediction of the rate of penetration using logistic regression algorithm of machine learning model," Arabian Journal of Geosciences, vol. 14, pp. 1-13, 2021.
[32] M. I. Guerra, F. M. de Araújo, J. T. de Carvalho Neto, and R. G. Vieira, "Survey on adaptative neural fuzzy inference system (ANFIS) architecture applied to photovoltaic systems," Energy Systems, pp. 1-37, 2022.
[33] M. Mohammadpourfard, A. Sami, and Y. Weng, "Identification of false data injection attacks with considering the impact of wind generation and topology reconfigurations," IEEE Transactions on Sustainable Energy, vol. 9, no. 3, pp. 1349-1364, 2017.