Scholarlink

Modern power grids are increasingly vulnerable to false data injection attacks (FDIAs), threatening automatic generation control (AGC). AGC ensures balance between power generation and consumption, making it a key cyberattack target. This study proposes a machine learning-based framework to detect and mitigate FDIAs using historical grid data. Models like logistic regression, SVM, and ensemble methods are used to detect and mitigate FDIAs in AGC. Mitigation strategies with these models ensure rapid recovery, enhancing AGC cybersecurity and protecting other critical infrastructure systems from evolving threats but experimental results confirm that logistic regression model outperforms the other models as it achieves consistently high accuracy, F1-scores, precision, and recall across all test sizes.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Efficient Detection and Mitigation of False Data Injection Attacks in Automatic Generation Control Using Machine Learning Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Akshat Agrawal,
  • Nimai Charan Patel

摘要

Modern power grids are increasingly vulnerable to false data injection attacks (FDIAs), threatening automatic generation control (AGC). AGC ensures balance between power generation and consumption, making it a key cyberattack target. This study proposes a machine learning-based framework to detect and mitigate FDIAs using historical grid data. Models like logistic regression, SVM, and ensemble methods are used to detect and mitigate FDIAs in AGC. Mitigation strategies with these models ensure rapid recovery, enhancing AGC cybersecurity and protecting other critical infrastructure systems from evolving threats but experimental results confirm that logistic regression model outperforms the other models as it achieves consistently high accuracy, F1-scores, precision, and recall across all test sizes.