Power Quality Prediction of Active Distribution Network Based on CNN-LSTM Deep Learning Model

Abstract

Aiming at the sequential and non-linear characteristics of power quality data over a long time span, a set of PQ evaluation and early warning system with DG distribution network based on deep learning is proposed. The intelligent power distribution network power quality monitoring and early warning system aims to realize the monitoring and forecasting and early warning functions of multiple indicators of power quality in the distribution network. First, use the sliding window to convert the power quality data into a number of square graphs with time as the scale; second, use the feature extraction advantages of the (Convolutional Neural Network, CNN) to extract the features of each square graph sample and extract it The characteristic information of is transformed into the input of (Long Short Term Memory, LSTM) in a time series sequence; Finally, according to the output of CNN, LSTM is used to complete the power quality data prediction of the active distribution network. Through an IEEE-13 node active distribution network simulation example with distributed power sources, this method decouples the feature extraction analysis and prediction tasks of power quality data, and simplifies the prediction work. Compared with the selected control model, it is significantly Improve the prediction accuracy.