Fixed effect model-based power consumption prediction method

Abstract

The present invention relates to a method for forecasting electricity consumption based on a fixed effect model, comprising the steps of: 1) loading electricity consumption data for N years, wherein the electricity consumption data includes daily electricity consumption data and daily temperature Data, shift data; 2) Construct a fixed effect model for each year of the loading year: 3) According to the obtained electricity consumption data of N years, the mean value of the intercept item, the model coefficient and the intercept of each year are obtained by fitting respectively Deviation value; 4) In the fixed effect model of each year As the daily basic power consumption, construct the regression equation of the daily basic power consumption with respect to the year, and obtain the daily basic power consumption of the year to be predicted according to the regression equation; 5) Construct according to the obtained daily basic power consumption of the year to be predicted The prediction equation of the year is used to predict the electricity consumption for each day of the year. Compared with the prior art, the present invention has the advantages of accurate prediction and the like.

Description

technical field [0001] The invention relates to the technical field of power grid electricity forecasting, in particular to an electricity consumption forecasting method based on a fixed-effect model. Background technique [0002] With the development of the economy and society and the improvement of people's living standards, the characteristics of electricity consumption in the metropolis of Shanghai have become increasingly prominent, and the impact of temperature on electricity load and electricity consumption has become more and more important. In recent years, during the peak summer season, the maximum air-conditioning load accounts for about 40% of the total load, and the continuous increase of air-conditioning load and proportion has become one of the main characteristics of Shanghai Power Grid. Quantitatively studying the impact of temperature changes on electricity consumption and determining the quantitative relationship between them is of great significance for p...

AI Technical Summary

Problems solved by technology

However, the existing research only establishes the linear relationship model between temperature and power consumption through statistical analysis, time series analysis, multiple regression analysis and other methods, without taking into account the fact that basic power consumption increases year by year, and the fact that power consumption varies with temperature in winter and summer. A non-linear trend that decreases or increases with an accelerating climb

Images