Research on electricity consumption forecasting model based on wavelet transform and multi-layer LSTM model

In order to formulate a reasonable power generation and transmission plan, and effectively prevent the waste of electricity resources, a power consumption prediction model based on wavelet transform and multi-layer LSTM is proposed. In this paper, the sample data is first denoised based on wavelet transform to eliminate the volatility of the electricity consumption data itself. Then, based on the pre-processed samples, the multi-layer LSTM model is used for training, and the proposed model is verified and predicted daily power consumption based on the power consumption of the area controlled by U.S. electric power company. The experimental results show that the prediction performance of this model is better than traditional LSTM and bidirectional LSTM. The mean square error is 0.019, and the coefficient of determination R2 is as high as 0.997. It also shows that wavelet denoising can further improve the prediction performance of the model.