Carbon Emission Prediction Model for Smart Energy Cities Based on Deep Learning

As the environmental protection situation is becoming increasingly serious, the environmental pollution caused by the carbon emissions of urban power users has become a common concern. Aiming at the problems of low accuracy and difficult parameter optimization of the current carbon emission prediction model for power users, a carbon emission prediction model PSO-CNN-LSTM based on the denoising of wavelet packet decomposition (WPD) is proposed. Firstly, wavelet packet decomposition is used to denoise the modeling data, and then the CNN-LSTM model is constructed to predict the carbon emission data. The CNN-LSTM model is then built to predict the carbon emission data. In order to solve the problem of the difficult selection of hyperparameters for the model, the Particle Swarm Optimization (PSO) algorithm is used to search for the optimal hyperparameter combinations for the model iteratively. It is verified that the proposed PSO-CNN-LSTM model based on WPD denoising is optimal in all four evaluation indexes and has a stronger generalization ability, which indicates that the model can be applied to the prediction of carbon emissions of urban electricity consumers.