Search

The widespread use of Phasor Measurement Units (PMUs) is considered one of the most important contributions to the quality of power system monitoring. PMUs are digital devices that provide synchronized phasor measurements time-referenced by the Global Positioning System (GPS). The lack of encryption in conventional GPS receivers used in PMUs makes them vulnerable to GPS Spoofing Attacks (GSAs) that cause the GPS receiver to lose track, resulting in a phase shift of all measurements of the affected PMU. Even small phase shifts can downgrade the performance of the state estimator, indicating their ability to propagate throughout the entire system. Therefore, ensuring the integrity of PMU measurements is of utmost importance. State-of-the-art statistical methods are insensitive to small phase shifts, and they become computationally intensive as the system size and the number of simultaneous attacks increase. This paper presents the first application of deep learning to simultaneously detect and mitigate the effects of GSAs against PMUs. The performance of the proposed method is evaluated on IEEE 14-, 57-, and 118-bus systems and compared to state-of-the-art statistical and deep learning methods. • A novel Transformer-based approach to detect and mitigate the effects of GSAs. • It has capable of detecting, identifying, and correcting the corrupted measurements. • The proposed methods address the entire possible range of attack-induced phase shift. • The performance of the proposed methods is evaluated against the statistical methods. [ABSTRACT FROM AUTHOR]

Accurately locating Forced Oscillations (FOs) source(s) in a large-scale power system is a challenging task, and an important aspect of power system operation. In this paper, a complementary use of Deep Learning (DL)-based and Dissipating Energy Flow (DEF)-based methods are proposed to localize forced oscillation source(s) using data from Phasor Measurement Units (PMUs), by tracing the forced oscillations source(s) on the branch level in the power system network. The robustness, effectiveness and speed of the proposed approach is demonstrated in a WECC 240-bus test system, with high renewable integration in the system. Several simulated cases were tested, including non-gaussian noise, partially observable system, and operational topology variations in the system which correspond to real-world challenges. Timely localization of forced oscillation at an early stage provides the opportunity for taking remedial reaction. The results show that without the information of system operational topology, the proposed method can achieve high localization accuracy in only 0.33 s. • A Deep-Learning based approach for forced oscillations is proposed. • It has reliable and robust performance in the presence of topology variation. • It significantly restricts the required information. • It is able to reliably detect multiple oscillation sources simultaneously. [ABSTRACT FROM AUTHOR]