Electronic device, building power load forecasting method based on gradient lift regression, and storage medium

Abstract

The invention provides an electronic device, a building power load forecasting method based on gradient lift regression, and a storage medium. The method comprises the following steps of: collecting the values of various factors affecting the electrical load corresponding to the predicted building on the forecast date,, wherein, the factors influencing the power load include temperature attributes, weekly attributes, festival attributes, humidity attributes and preset power supply output power; normalizing the values of the collected factors to obtain the normalized values of the factors; according to the gradient lifting regression prediction model trained in advance, the electric load value is predicted to predict the maximum electric load value of the predetermined building on the corresponding prediction day. The method can effectively improve the accuracy of power load forecasting and provide reference data for the construction and promotion of smart grid.

Description

Technical field [0001] The present invention relates to the field of power load prediction, in particular to an electronic device, a building power load prediction method based on gradient lifting regression, and a storage medium. Background technique [0002] Power load forecasting is an important part of power research, and it plays a key role in the effective operation of the power market. With the advancement of science and technology and the needs of economic development, the construction of smart grids has kicked off, thereby improving the utilization rate of energy and promoting the optimal allocation of resources. [0003] At present, the commonly used forecasting methods include empirical forecasting technology, linear regression forecasting technology, time series forecasting technology, etc. Among them, empirical forecasting technology mainly relies on the judgment of experts or expert groups, and the existing forecast errors are relatively high. Linear regression predi...

AI Technical Summary

Problems solved by technology

Linear regression forecasting refers to the regression analysis method in mathematical statistics, that is, through the statistical analysis of the observed data of the variables, the linear correlation relationship between the variables is determined, so as to achieve the purpose of forecasting. This method cannot classify and synthesize the power load. Therefore, it is not suitable for different urban load forecasting

Time series forecasting technology is different from linear regression technology. Both dependent variable (prediction target) and independent variable can be random variables, which cannot be associated with variables that affect load changes, resulting in inaccurate forecasting results

Images