Authors: Sunitha Basodi; Song Tan; WenZhan Song; Yi Pan
Addresses: Department of Computer Science, Georgia State University, Atlanta, GA, USA ' Department of Computer Science, Georgia State University, Atlanta, GA, USA ' School of Electrical and Computer Engineering , University of Georgia, Atlanta, GA, USA ' Department of Computer Science, Georgia State University, Atlanta, GA, USA
Abstract: Cybersecurity in smart grids plays a crucial role in determining its reliable functioning and availability. Data integrity attacks at the physical layer of smart grids are mainly addressed in this paper. State vector estimation (SVE) methods are widely used to detect such attacks, but such methods fail to identify attacks that comply with physical properties of the grid, known as unobservable attacks. In this paper, we formulate a distance measure to be employed as the cost function in deep-learning models using feed-forward neural network architectures to classify malicious and secured measurements. Efficiency and performance of these models are compared with existing state-of-the-art detection algorithms and supervised machine learning models. Our analysis shows better performance for deep learning models in detecting centralised data attacks.
Keywords: smart grids; bad data detection; state vector estimation; SVE; deep learning; IEEE test bus systems; matpower; Keras with TensorFlow.
International Journal of Security and Networks, 2020 Vol.15 No.1, pp.15 - 24
Received: 10 Nov 2018
Accepted: 14 Mar 2019
Published online: 09 Apr 2020 *