Locational Detection of the False Data Injection Attack in a Smart Grid: A Multilabel Classification Approach | IEEE Journals & Magazine | IEEE Xplore

Locational Detection of the False Data Injection Attack in a Smart Grid: A Multilabel Classification Approach


Abstract:

State estimation is critical to the monitoring and control of smart grids. Recently, the false data injection attack (FDIA) is emerging as a severe threat to state estima...Show More

Abstract:

State estimation is critical to the monitoring and control of smart grids. Recently, the false data injection attack (FDIA) is emerging as a severe threat to state estimation. Conventional FDIA detection approaches are limited by their strong statistical knowledge assumptions, complexity, and hardware cost. Moreover, most of the current FDIA detection approaches focus on detecting the presence of FDIA, while the important information of the exact injection locations is not attainable. Inspired by the recent advances in deep learning, we propose a deep-learning-based locational detection architecture (DLLD) to detect the exact locations of FDIA in real time. The DLLD architecture concatenates a convolutional neural network (CNN) with a standard bad data detector (BDD). The BDD is used to remove the low-quality data. The followed CNN, as a multilabel classifier, is employed to capture the inconsistency and co-occurrence dependency in the power flow measurements due to the potential attacks. The proposed DLLD is “model-free” in the sense that it does not leverage any prior statistical assumptions. It is also “cost-friendly” in the sense that it does not alter the current BDD system and the runtime of the detection process is only hundreds of microseconds on a household computer. Through extensive experiments in the IEEE bus systems, we show that DLLD can perform locational detection precisely under various noise and attack conditions. In addition, we also demonstrate that the employed multilabel classification approach effectively enhances the presence-detection accuracy.
Published in: IEEE Internet of Things Journal ( Volume: 7, Issue: 9, September 2020)
Page(s): 8218 - 8227
Date of Publication: 27 March 2020

ISSN Information:

Funding Agency:


I. Introduction

The power system is a fundamental economic-social infrastructure. The recent trends of Industrial Internet-of-Things (IIoT) technology have profoundly transformed the conventional power system in the last decades. In particular, the latest advances in smart grids extensively integrate the advanced information and communication technology (ICT) [1] with the conventional power system, which significantly increase the grid efficiency and reliability. However, the new ICT systems employed by smart grids as well as other IIoT networks are facing great security challenges especially under the mounting threats of cyberattacks. State estimation, which calculates the state of the power network system from the raw measurements gathered by the supervisory control and data acquisition (SCADA) system [2], plays a very essential role in the control center. In particular, compromised system state estimation may interfere the operation of power systems, since many power system applications (such as economic dispatch, contingency analysis, etc.) rely on the results of state estimation [3]. Liang et al. [4] and Deng et al. [5] presented comprehensive surveys on the impacts of cyberattacks on state estimation, e.g., line congestion [6], power outage [7], communication block [8], etc.

Contact IEEE to Subscribe

References

References is not available for this document.