False Data Injection Attacks (FDIA) detection by Deep Learning Techniques in Smart Grids: survey

Hesham Haider, Al-Marhabi Zaid Ali, Ayeda Al-Hmadi

الملخص

Smart grids are becoming increasingly popular due to their ability to enhance energy efficiency and reduce costs. However, they also pose new challenges to the security of the grid. One of the main threats to smart grids is False Data Injection Attacks (FDIA), which can cause serious damage to the grid if not detected and prevented in a timely manner.

Deep learning techniques have shown great promise in detecting FDIA in smart grids due to their ability to automatically learn and detect patterns in large and complex datasets. In this research project, we review the existing deep learning techniques used to detect FDIA in smart grids. We provide an overview of the various deep learning models, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Autoencoders, that have been used to detect FDIA.

We also discuss the challenges and limitations of using deep learning techniques for FDIA detection in smart grids, such as the lack of large-scale datasets and the need for more explainable models. Finally, we propose future research directions in this field, such as the development of hybrid models combining deep learning with other techniques to improve the accuracy and efficiency of FDIA detection.