Resident load ultra-short-term prediction method

Abstract

A resident load ultra-short-term prediction method comprises the following steps: S1, acquiring daily historical electricity consumption data of resident electricity consumption loads, performing clustering analysis based on daily electricity consumption data of a day-ahead time period to obtain class load electricity consumption data, S2, selecting load power consumption data of the same category as the day to be measured, and performing wavelet decomposition to obtain three components; and S3, training the sum component by using LSTM to respectively obtain prediction results of the three components of the day to be measured, and superposing the prediction results of the sum component and the three components to obtain a prediction result of the day to be measured. According to the design, the precision of ultra-short-term prediction of the power consumption load of a single household is effectively improved.

Description

technical field [0001] The invention relates to the technical field of distribution network load forecasting, in particular to a method for ultra-short-term forecasting of residential loads, which is mainly suitable for improving the accuracy of load forecasting. Background technique [0002] Traditional load forecasting mainly includes two methods. One is the data-driven power load forecasting method, which uses various advanced machine learning algorithms to realize power load forecasting on the day to be forecasted. This type of method can be implemented based on a single machine learning algorithm, or based on a combination of multiple machine learning algorithms. In order to improve the forecasting accuracy, with the advantages of each load forecasting algorithm, the load forecasting method based on a variety of machine learning combination algorithms has been greatly developed. For example, some methods use the back propagation (BP) neural network to analyze the histo...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the defects and problems of low load forecasting accuracy existing in the prior art, and provide a super-short-term load forecasting method for residents with high load forecasting accuracy

Images