Long short‐term memory‐based robust and qualitative modal feature identification of non‐stationary low‐frequency oscillation signals in power systems

Abstract

Low-frequency oscillation (LFO) analysis has become increasingly important in large scale power systems. The current LFO analysis methods regard the measured signal as stationary signal. Some methods, such as Prony and HHT, are too slow for online application. In order to solve these problems, based on the long short-term memory neural network (LSTM), this paper proposes a method to identify LFO modal features rapidly. It is the first time in this field to formulate LFO modal feature classification problem rather than LFO modal identification problem. In order to realize it, first, LFO's frequency and attenuation factor are artificially divided into 12 and 4 segments, respectively. For each segment, more than 20,000 data are generated and tagged as training set and test set. Then two bi-directional LSTM networks are constructed separately, and each network is trained alone with the data of the training set. Finally, the proposed method is tested and verified with the data from the test set, power systems simulation, and phasor measurement unit (PMU) of real power systems. The test results prove effectiveness of the proposed method and its advantage is demonstrated through comparison with the Prony, FFT and EDSNN methods.