Towards Resilient and Secure Smart Grids against PMU Adversarial Attacks: A Deep Learning-Based Robust Data Engineering Approach

Abstract

In an attempt to provide reliable power distribution, smart grids integrate monitoring, communication, and control technologies for better energy consumption and management. As a result of such cyberphysical links, smart grids become vulnerable to cyberattacks, highlighting the significance of detecting and monitoring such attacks to uphold their security and dependability. Accordingly, the use of phasor measurement units (PMUs) enables real-time monitoring and control, providing informed-decisions data and making it possible to sense abnormal behavior indicative of cyberattacks. Similar to the ways it dominates other fields, deep learning has brought a lot of interest to the realm of cybersecurity. A common formulation for this issue is learning under data complexity, unavailability, and drift connected to increasing cardinality, imbalance brought on by data scarcity, and fast change in data characteristics, respectively. To address these challenges, this paper suggests a deep learning monitoring method based on robust feature engineering, using PMU data with greater accuracy, even within the presence of cyberattacks. The model is initially investigated using condition monitoring data to identify various disturbances in smart grids free from adversarial attacks. Then, a minimally disruptive experiment using adversarial attack injection with various reality-imitating techniques is conducted, inadvertently damaging the original data and using it to retrain the deep network, boosting its resistance to manipulations. Compared to previous studies, the proposed method demonstrated promising results and better accuracy, making it a potential option for smart grid condition monitoring. The full set of experimental scenarios performed in this study is available online.

Getting a Better Sense of Data Drift in Dynamic Systems: Sequence-Based Deep Learning for Monitoring Slowly Evolving Degradation Processes

“…In this context, 11 time domain features that were the same as those used in previous work [8] (see [8], Section 2.3) were extracted. Similarly, the same denoising, outlier removing, and scaling steps applied in [8] were followed to make sure the data were ready for DL model training. Accordingly, Figure 1b is an example of extracted features from the life cycle in Figure 1a, as some degradation patterns clearly can be seen in this situation.…”

“…In this work, data were subjected to preprocessing, making it easier to extra possible degradation signs at first glance. In this context, 11 time domain feature were the same as those used in previous work [8] (see [8], Section 2.3) were extr Similarly, the same denoising, outlier removing, and scaling steps applied in [8] we lowed to make sure the data were ready for DL model training. Accordingly, Figur an example of extracted features from the life cycle in Figure 1a, as some degrad patterns clearly can be seen in this situation.…”

Optimal Placement of μPMUs in Distribution Networks with Adaptive Topology Changes

“…One node is a generator bus and the others are load buses (Figure 12). The algorithm reaches the observability and it gives 12 µPMUs implemented in nodes 3,29,2,4,9,12,15,19,22,25,33,30. SORI is equal to 46.…”

“…Addressing communication security issues and noise interference is essential for maintaining the reliability and trustworthiness of µPMU measurements and, by extension, the effectiveness of the power grid monitoring system [22,23]. Robust security measures and data quality assurance techniques are critical components of a resilient and accurate monitoring infrastructure [24,25].…”