IRO Journals
Journal of Electrical Engineering and Automation

Reliable Detection of Cyber Threats in Smart Grids Using a Hybrid XGBoost and LSTM Framework

Open Access
Published: 16 October, 2026
Pages: 272-285
  • Arul Princy A. , Arul Princy A.
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Veera Ramana M. , Veera Ramana M.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Nithish R. , Nithish R.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Vishnu Sankar R. Vishnu Sankar R.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
view PDF
view PDF

How to Cite

A., Arul Princy, Veera Ramana M., Nithish R., and Vishnu Sankar R. 2026. “Reliable Detection of Cyber Threats in Smart Grids Using a Hybrid XGBoost and LSTM Framework”. Journal of Electrical Engineering and Automation 8 (4): 272-85. https://doi.org/10.36548/jeea.2026.4.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Smart Grid Cybersecurity
Cyber Threat Detection
XGBoost
Long Short-Term Memory (LSTM)
Hybrid Deep Learning
False Data Injection Attack
Real-time Monitoring

Abstract

The smart grid utilizes communication, measurement, and automation techniques that help to monitor the power system but increase vulnerability to cyber attacks. FDIA and DoS are two types of cyber attack that either tamper with measurements or limit access to information and therefore need a detection technique capable of capturing the dynamics of measurements. In this study, a hybrid classification model that combines XGBoost and LSTM is introduced to classify smart-grid observations as normal state, FDIA state, and DoS state. The XGBoost algorithm will be utilized for performing static feature analysis, and the LSTM will model the temporal dependencies based on the consecutive measurement windows. The output of the two algorithms is then merged using the weighted decision fusion method. The proposed scheme is evaluated based on data created based on IEEE 39-Bus New England power system test case, after applying preprocessing techniques such as missing values interpolation, min-max normalization, ten-sample windows, and 80% training and 20% testing ratio. Experimental results report an overall accuracy of 82.12%, with class-wise F1-scores between 0.81 and 0.82 and a false-positive rate of 5.1%. The proposed system is further combined with a real-time monitoring interface using Flask, email alerts through SMTP, and logging events. This monitoring system has achieved an average latency of 0.23 seconds per sample, 1.5 seconds average alert time, ability to handle up to 50 simultaneous sessions, and 99.7% average uptime during the experiment.

References

  1. Ruan, Jiaqi, Gaoqi Liang, Junhua Zhao, Huan Zhao, Jing Qiu, Fushuan Wen, and Zhao Yang Dong. "Deep learning for cybersecurity in smart grids: Review and perspectives." Energy Conversion and Economics 2023, vol. 4, no. 4: 233-251.
  2. Nasir, Qassim, Manar Abu Talib, Muhammad Arbab Arshad, Tracy Ishak, Romaissa Berrim, Basma Alsaid, Youssef Badway, and Omnia Abu Waraga. "Comparison of Deep Learning Algorithms for Site Detection of False Data Injection Attacks in Smart Grids." Energy Informatics 2024, vol. 7, no. 1: 71.
  3. He, Youbiao, Gihan J. Mendis, and Jin Wei. "Real-Time Detection of False Data Injection Attacks in Smart Grid: A Deep Learning-Based Intelligent Mechanism." IEEE Transactions on Smart Grid 2017, vol. 8, no. 5: 2505-2516.
  4. Niu, Xiangyu, Jiangnan Li, Jinyuan Sun, and Kevin Tomsovic. "Dynamic Detection of False Data Injection Attack in Smart Grid using Deep Learning." IEEE power energy society innovative smart grid technologies conference (ISGT), 2019, 1-6.
  5. Yang, Liqun, You Zhai, and Zhoujun Li. "Deep Learning for Online AC False Data Injection Attack Detection in Smart Grids: An Approach using LSTM-Autoencoder." Journal of Network and Computer Applications 2021, vol. 193: 103178.
  6. Singh, Rashi, Nasib Singh Gill, and Preeti Gulia. "Attentional LSTM-Ensemble Architecture for Intrusion Detection in Smart Grids." Scientific Reports 2025, vol. 15, no. 1: 41977.
  7. Gupta, Tania, Richa Bhatia, Sachin Sharma, Ch Rami Reddy, Kareem M. AboRas, and Wael Mobarak. "A Data-Driven Ensemble Technique for the Detection of False Data Injection Attacks in the Smart Grid Framework." Frontiers in Energy Research 2024, vol. 12: 1366465.
  8. Alenazi, Mordi, and Shailendra Mishra. "Cyberatttack Detection and Classification in IOT Systems Using XGBoost And Gaussian Naïve Bayes: A Comparative Study." Engineering, Technology Applied Science Research 2024, vol. 14, no. 4: 15074-15082.
  9. Ghadi, Yazeed Yasin, Tehseen Mazhar, Tariq Shahzad, Ines Hilali Jaghdam, Sanwar Khan, Muhammad Amir Khan, and Habib Hamam. "A Hybrid AI-Blockchain Security Framework for Smart Grids." Scientific reports 2025, vol. 15, no. 1: 20882.
  10. Li, Yang, Xinhao Wei, Yuanzheng Li, Zhaoyang Dong, and Mohammad Shahidehpour. "Detection of False Data Injection Attacks in Smart Grid: A Secure Federated Deep Learning Approach." IEEE Transactions on Smart Grid 2022, vol. 13, no. 6: 4862-4872.
  11. Singh, Kamal. "Detection Of Cyber and Physical Disturbances in Power Systems Using Data-Driven Deep Learning Methods." International Journal of Critical Infrastructure Protection 2026: 100844.
  12. Texas AM University Electric Grid Test Case Repository, “IEEE 39-Bus System,” Department of Electrical and Computer Engineering, Texas AM University. Available https://electricgrids.engr.tamu.edu/electric-grid-test-cases/ieee-39-bus-system/
  13. Raza, Mubashar, Muhammad Jasim Saeed, Muhammad Bilal Riaz, and Muhammad Awais Sattar. "Federated Learning for Privacy-Preserving Intrusion Detection in Software-Defined Networks." IEEE Access 2024, vol. 12: 69551-69567.
  14. Mohammed, Saad Hammood, Mandeep S. Jit Singh, Abdulmajeed Al-JumailyInvestigation, Mohammad Tariqul Islam, Md Shabiul Islam, Abdulmajeed M. Alenezi, Mohamad A. Alawad, and Muaadh A. Alsoufi. "IG-APSO-DNN: Deep Learning Intrusion Detection Model to Detect False Data Injection Attacks in Smart Grids." Ad Hoc Networks 2025: 104053.