Energy consumption structure prediction method based on grey QRNN correction of component data

Abstract

The invention discloses an energy consumption structure prediction method based on grey QRNN correction of component data, and the method comprises the steps: 1, extracting the energy consumption structure component data of any region, and carrying out the data preprocessing of symmetric logarithm ratio transformation; 2, carrying out preliminary prediction on the preprocessed data by using a grayGM (1, 1) model, and calculating a residual error of the data; 3, establishing a quantile regression neural network prediction model for the residual sequence to obtain conditional quantiles under different quantiles; 4, performing probability density prediction by taking the conditional quantiles under different quantiles as input variables of an Epanechnikov kernel function to obtain a residualprediction value; 5, combining the grey model prediction value and the residual prediction value to obtain correction data of the data after energy consumption structure processing; and obtaining a final energy consumption structure component data prediction value after inverse transformation. According to the method, the energy consumption structure prediction model with an accurate prediction effect can be obtained, so that favorable help can be provided for reasonable configuration and effective development of energy.

Description

technical field [0001] The invention belongs to the field of energy consumption structure prediction, in particular to an energy consumption structure prediction method based on gray QRNN correction of component data. Background technique [0002] Energy is an indispensable and important resource for the development of human economy and the progress of social civilization, and it is very important in the modernization drive. Energy consumption system is an important part of energy, environment and social system. With the continuous development of society, the demand for energy is increasing, and the contradiction between energy supply and demand is becoming more and more obvious. Scientific prediction of energy consumption is of great significance to social progress, economic development and macro policy formulation. [0003] Many scholars at home and abroad have done a lot of research in the field of energy consumption prediction, which can be roughly divided into statist...

AI Technical Summary

Problems solved by technology

However, it is difficult for a single forecasting method to achieve excellent forecasting results in all situations

And in the existing research, many scholars focus on the research on the absolute amount of energy consumption, and there are few studies on the structure of energy consumption.

Images