An LSTM-ARDL Based Two-Step Prediction Algorithm for Electricity-Carbon Emissions in Industry and Public Buildings

A new algorithm is proposed 2 step forecast method to combine the LSTM and ARDL algorithms to predict the carbon emission data based on all the energy consumption data. The accuracy and computational time consumption of the proposed algorithm are verified through empirical research. The results show that the proposed algorithm can improve the accuracy of carbon emission prediction or reduce the computational time required for prediction with the same accuracy not only for industry but also for public buildings. The work in this paper shows a rather prospect for a low-carbon society.