Analysis and Value Evaluation of Carbon Emission Reduction Strategies in the Power Industry Based on Real Options Theory and XGboost Algorithm

Abstract

China, as the world’s largest energy consumer, has made significant commitments regarding carbon peaking and carbon neutrality. In order to realize the goal of “dual carbon,” this paper proposes a method for analyzing and evaluating carbon emission reduction strategies in the electric power industry based on physical options theory and the XGBoost algorithm. Starting from the study of carbon emission reduction strategies for power enterprises, the model is oriented towards investment in energy-saving and emission reduction technologies for thermal power, aiming to construct the least-cost carbon emission reduction strategy. Additionally, it comprehensively considers changes in carbon trading mechanisms and the uncertainty of investment budgets for emission reduction, integrating machine learning algorithms to assess the emission reduction value of enterprises during the research period. The aim is to provide theoretical guidance and strategic suggestions for existing thermal power enterprises to cope with the implementation of carbon trading mechanisms. Finally, through case analysis, the effectiveness of this method is validated.