Zone area daily power consumption prediction method based on weekly coefficient linear regression model

Abstract

The invention is a zone area daily power consumption prediction method based on a weekly coefficient linear regression model. The method comprises the following steps of establishing the "weekly scale coefficient group K" of a zone area according to a standard week; obtaining the corrected electricity consumption of the historical date according to the "weekly scale coefficient group K"; establishing an n-element linear regression model for an influencing factor; obtaining historical meteorological data near the predicted date through querying a meteorological database; substituting the historical meteorological data obtained from S2 near the predicted date into a formula; fitting a linear regression equation by a least square formula and calculating each constant in the linear regression equation; and substituting the constants and the influencing factor into the n-element linear regression model to obtain the corrected electricity consumption of the predicated date, and finally, substituting the corrected daily electricity consumption of the predicted date into the "weekly scale coefficient group K" to obtain the predicted consumption of the predicted date. The method is advantaged by being simple and high in accuracy.

Description

technical field [0001] The invention relates to a method for predicting daily power consumption in a station area based on a linear regression model of the day of the week coefficient, and belongs to the technical field of power grid power consumption. Background technique [0002] Power consumption forecasting is the key basis for power grid companies to formulate comprehensive production plans and formulate business plans. Reasonable and accurate forecast conclusions will bring positive effects to the company's business decisions, otherwise it will lead to deviations from the company's business strategies, so it will affect future quarters or Annual electricity consumption forecasts are crucial. An overview of domestic and foreign market forecasting technologies shows that the existing power consumption forecasting technologies can be classified into three categories, but none of them can solve the key problems of power consumption forecasting. [0003] The first type of ...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is that the forecasting algorithm is complex, experience cannot be quantified to a specific forecasting model, and the forecasted results have large deviations and low accuracy

Images