Machine learning can analyze and study the huge amount of big data on electricity, explore and mine the correlation between electricity data, and then analyze the current situation and predict the future values of certain electric power industry indicators. In this paper, various social, economic and industrial indicators affecting the grid emission factors are derived through algorithmic analysis of the grid emission factors. The Gaussian process regression analysis algorithm was used to compare and analyze the collected electricity data, focusing on five aspects of regression effects, including root mean square error, mean square error, mean absolute error, fitting coefficient, and running time, to obtain the optimal regression model parameters. Finally, the trained model was completed to predict the emission factors of the East China Power Grid from 2020 to 2060.
Paper
Full text
Emission factors measurement of regional power grid based on Gaussian process regression
Semantic Scholar · Environmental Science · 2023
Abstract
Machine learning can analyze and study the huge amount of big data on electricity, explore and mine the correlation between electricity data, and then analyze the current situation and predict the future values of certain electric power industry indicators. In this paper, various social, economic and industrial indicators affecting the grid emission factors are derived through algorithmic analysis of the grid emission factors. The Gaussian process regression analysis algorithm was used to compare and analyze the collected electricity data, focusing on five aspects of regression effects, including root mean square error, mean square error, mean absolute error, fitting coefficient, and running time, to obtain the optimal regression model parameters. Finally, the trained model was completed to predict the emission factors of the East China Power Grid from 2020 to 2060.