Load prediction method and device, computer readable storage medium and electronic equipment

Abstract

The invention discloses a load prediction method and device, a computer readable storage medium and electronic equipment, and the method comprises the steps: obtaining at least one sample prediction day and at least one sample historical data set corresponding to the prediction day, and enabling the at least one sample historical data set to be in one-to-one correspondence with the at least one sample prediction day; according to a load prediction method, respectively carrying out load prediction on the at least one sample historical data set, and determining at least one load prediction data set corresponding to the load prediction method; determining evaluation data corresponding to the load prediction method according to the at least one sample historical data set and the at least one load prediction data set corresponding to the load prediction method; and determining a target load prediction method corresponding to the prediction day according to the evaluation data corresponding to each load prediction method, the target load prediction method being used for carrying out load prediction on the prediction day. By means of the technical scheme, different load prediction methods can be evaluated, and the load prediction method with the good load prediction effect is obtained.

Description

technical field [0001] The invention relates to the field of energy technology, in particular to a load forecasting method, device, computer-readable storage medium and electronic equipment. Background technique [0002] Power load forecasting is a series of forecasting work based on power load. It is an important part of power system planning and the basis of power system economic operation. At present, the spot power market has reached the time-point granularity, and Shanxi, Sichuan and other regions require it to reach 15 minutes, which puts forward higher requirements for the accuracy of load forecasting. [0003] At present, load forecasting is mainly carried out through intelligent algorithms, such as using neural network / deep learning and other supervised / unsupervised algorithms to automatically analyze sample data, explore and discover its internal laws, and then predict the future. [0004] However, the accuracy of load forecasting by intelligent algorithms is high...

AI Technical Summary

Problems solved by technology

[0004] However, the load forecasting accuracy of intelligent algorithms is highly dependent on the amount of data, resulting in relatively low load forecasting accuracy

Images