Detection and Identification of Cyber and Physical Attacks on Distribution Power Grids With PVs: An Online High-Dimensional Data-Driven Approach

Abstract

Cyber and physical attacks threaten the security of distribution power grids. The emerging renewable energy sources such as photovoltaics (PVs) introduce new potential vulnerabilities. Based on the electric waveform data measured by waveform sensors in the distribution power networks, in this paper, we propose a novel high-dimensional data-driven cyber physical attack detection and identification approach (HCADI). Firstly, we analyze the cyber and physical attack impacts (including cyber attacks on the solar inverter causing unusual harmonics) on electric waveforms in distribution power grids. Then, we construct a high dimensional streaming data feature matrix based on signal analysis of multiple sensors in the network. Next, we propose a novel mechanism including leverage score based attack detection and binary matrix factorization based attack diagnosis. By leveraging the data structure and binary coding, our HCADI approach does not need the training stage for both detection and the root cause diagnosis, which is needed for machine learning/deep learning-based methods. To the best of our knowledge, it is the first attempt to use raw electrical waveform data to detect and identify the power electronics cyber/physical attacks in distribution power grids with PVs.

Guest Editorial Special Section on Cybersecurity of Power Electronics Through Hardware Hardening

“…In [3], Li et al describe an online data-driven algorithm for detecting and identifying both cyber and physical attacks without the need for the training found in artificial intelligence/machine learning methods. It directly uses electrical waveform data to perform these determinations and is thus suitable for online deployment in power electronics hardware such as solar inverters.…”

Low-Rank Methods in Event Detection With Subsampled Point-to-Subspace Proximity Tests

“…], and fewer still, which allow for missing data [63], [64]. Some of the recent ones [30], [33]- [35], [65], [66] also consider low-rank factorizations, albeit without subsampling. From the methodological works, we differ in our assumptions (uniform, rather than Gaussian noise), focus on efficient algorithms (subsampled subspace proximity testers) for the test, and our PAC guarantees.…”

Cyber–Physical Security of Powertrain Systems in Modern Electric Vehicles: Vulnerabilities, Challenges, and Future Visions

“…As data-driven methods do not require explicit physical models, they can cope with complex, complicated, and heterogeneous phenomena. There are many data-driven methods for the security issues, such as the geometrically designed residual filter [46], signal analytics based [152], generalized likelihood ratio [153], the cumulative sum (CUSUM) [154], leverage score [155], influential point selection [156], support vector machine (SVM) [121], Gaussian mixture model (GMM) [122], neural networks [123], machine learning [121], deep learning [157], and so on.…”