Scholarlink

<p>This paper aims at addressing the detection of false data attacks (FDAs) in power system. While improving the operation of the power system, the integration of multi-layered cyber-physical networks poses huge security risks. In particular, the FDAs can fool the Chi-square detector-based detection mechanism by manipulating communication layer data. For this reason, this paper focuses on proposing a novel spatial–temporal features-based detection framework against false data attacks (FDAs). The proposed detection framework consists of two steps as follows: Kepler Optimization Algorithm (KOA)-convolutional neural networks (CNN)-based spatial features extraction; bidirectional gate recurrent unit (BiGRU)-based temporal features extraction. To enhance the performance of extracting spatial features in CNN, KOA is introduced to optimize the related parameters of CNN, such as learning rate and convolution kernel size etc. Different traditional GRU, a BiGRU model is developed to extract the forward and backward temporal features. In addition, an Attention mechanism is introduced to focus on important information of feature data. Through the bilevel extraction of spatio-temporal features, the proposed detection framework can identify the normal or abnormal data in power system. Finally, simulation cases on IEEE 14-bus and 118-bus grid system are provided to verify the effectiveness of the proposed KOA-CNN-BiGRU-Attention framework. Compared with existing detection models, such as GCN and GGNN-GAT, accuracy, precise, F1-score, and recall under proposed detection model can be improved.</p>

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

A novel detection mechanism against malicious attacks by using spatio and temporal topology information

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月22日

查看全文
  • Qingfeng Wu,
  • Shufa Zhuang,
  • Xinyu Wang

摘要

This paper aims at addressing the detection of false data attacks (FDAs) in power system. While improving the operation of the power system, the integration of multi-layered cyber-physical networks poses huge security risks. In particular, the FDAs can fool the Chi-square detector-based detection mechanism by manipulating communication layer data. For this reason, this paper focuses on proposing a novel spatial–temporal features-based detection framework against false data attacks (FDAs). The proposed detection framework consists of two steps as follows: Kepler Optimization Algorithm (KOA)-convolutional neural networks (CNN)-based spatial features extraction; bidirectional gate recurrent unit (BiGRU)-based temporal features extraction. To enhance the performance of extracting spatial features in CNN, KOA is introduced to optimize the related parameters of CNN, such as learning rate and convolution kernel size etc. Different traditional GRU, a BiGRU model is developed to extract the forward and backward temporal features. In addition, an Attention mechanism is introduced to focus on important information of feature data. Through the bilevel extraction of spatio-temporal features, the proposed detection framework can identify the normal or abnormal data in power system. Finally, simulation cases on IEEE 14-bus and 118-bus grid system are provided to verify the effectiveness of the proposed KOA-CNN-BiGRU-Attention framework. Compared with existing detection models, such as GCN and GGNN-GAT, accuracy, precise, F1-score, and recall under proposed detection model can be improved.