A spatio-temporal method based on Robust Three-stage Dynamic Mode Decomposition (RTDMD) is proposed to improve the modal parameter estimation of synchrophasor data in the presence of noise, missing data and outliers. The proposed method is based on the PMU correlated spatio-temporal data to estimate missing information using an iterative singular value decomposition (SVD) combined with the adjustment of the reduced Koopman operator. Moreover, it is proposed to identify and correct outliers using an inherent statistical extension of the SVD-based Mahalanobis distance. As a result of the proposed enhancements, modal parameters such as damping and power system oscillation frequency are extracted as a byproduct of the RTDMD algorithm process. Data resulting from real-time digital simulators (RTDS) with self-clearing three-phase fault and Phasor Measurement Units (PMUs) of Low-Frequency Oscillation (LFO) incidents at hydroelectric power plants are used to illustrate the effectiveness of the proposed method over other well-established methods.
In this paper, a long short-term memory (LSTM)-based method with a multi-input tensor approach is used for the classification of events that affect the power quality (PQ) in power systems with distributed generation sources. The considered events are line faults (one line, two lines, and three lines faulted), islanding events, sudden load variations, and generation tripping. The proposed LSTM-based method was trained and tested using the signals produced by the events simulated in a study system with distributed generation sources via PSCAD®. Then, noise with different levels was added to the testing set for a thorough assessment, and the results were compared with other well-known methods such as convolutional and simple recurrent neuronal networks. The LSTM-based method with multi-input proved to be effective for event classification, achieving remarkable classification performance even in noisy conditions.