Medium and long term prediction of carbon emissions from thermal power generation based on grey correlation and PB neural network algorithm

To achieve the goal of "carbon peaking and carbon neutrality", it is urgent to carry out research on the accounting methods of carbon emissions from energy consumption. In this paper, based on the data of 1997-2020 thermal carbon emissions, per capita GDP, total population and thermal power generation of a province in China, combined with the grey correlation prediction model and BP neural network prediction model, the thermal carbon emissions of the province in the next 15 years are accurately predicted, and the time of carbon peak is determined and analyzed.In order to improve the prediction accuracy, firstly, grey correlation was used to analyze the influence of various factors on the emission of pyroelectric carbon, and then grey prediction model was used to predict the change trend of factors strongly correlated with the emission of pyroelectric carbon in the next 15 years. The obtained results were taken as the input layer data of BP neural network, and the trend extrapolation method of BP neural network model was used to predict the emission of pyroelectric carbon.It is estimated that carbon emissions from thermal power generation will increase first and then decrease in the next 15 years.