ARIMA-LSTM Line Loss Anomaly Analysis Method Based on Wavelet Decomposition

Abstract

One of the basic functions of power grid companies is to provide safe and reliable electrical energy. Line loss is a significant indicator for evaluating the performance of power transmission grids. It reflects the comprehensive capabilities of grid planning, operation and power enterprise management. Therefore, this paper proposes an ARIMA-LSTM line loss anomaly analysis method based on wavelet decomposition. First, wavelet transform is applied to decompose data to obtain high-frequency components and low-frequency components. Then we use ARIMA to predict the high-frequency components, and use LSTM to predict low-frequency components. Then wavelet transform is applied to reconstruct predicted values to obtain the predicted values of line loss data. Finally, the original data and predicted data are compared, and if the difference between the two is greater than the set threshold, it is considered as abnormal. Experiments with real data sets show that the proposed method has a good anomaly detection effect.