Harmonic Emission Level Estimation Method Based on CNN-LSTM Algorithm

In order to realize the effective prediction of harmonic emission level in power system, a harmonic emission level estimation method based on CNN-LSTM algorithm is proposed. The harmonic voltage and harmonic current data at the point of common connection are input into the CNN-LSTM algorithm, and the data features are extracted in the convolutional neural network layer of the algorithm model, and time modeling and prediction are carried out in the long short-term memory network layer, finally getting user and system harmonic emission levels. Comparative analysis of the simulation experiments and other algorithmic model estimation results shows that the proposed model predicts harmonic voltage emission levels on both side with smaller errors and higher stability, realizing the effective monitoring and assessment of power system harmonics and verifying the effectiveness.