8th International Conference on Advanced Power System Automation and Protection (APAP2019)

967 / 2019-04-30 22:51:20

Prediction for the Maximum Frequency Deviation of Post-disturbance Based on the Long Short-term Memory Network

long short-term memory network;,the maximum frequency deviation of post-disturbance;,the appearance time of the maximum frequency deviation;,time series.

A method based on the long short-term memory network (LSTM) to predict the maximum frequency deviation and its occurrence time of post-disturbance is proposed. In this paper, the inertial center frequency of 0-1s after disturbance is used as input, which substantially reduces the amount of data acquired from the system. Utilizing the memory characteristics of the long short- term memory network, this method extracts the time relationship between the disturbed frequencies, which provides a new method for predicting the maximum frequency deviation and its occurrence time of the disturbed system.