Heat supply energy consumption cycle prediction method based on generative adversarial network

Abstract

The invention discloses a heat supply energy consumption cycle prediction method based on a generative adversarial network. The method comprises the steps: constructing a historical heat supply energy consumption data set, and dividing a training set and a test set; normalizing the data set, dividing the normalized data set by using a sliding window, and constructing a historical energy consumption training set; constructing a generative adversarial network, sequentially taking out each section of training sequence from the historical energy consumption training set, and inputting the training sequence into the generative adversarial network for training; and performing normalization processing and sliding window division on the test set, inputting the test set into the trained generative adversarial network model to perform test and parameter adjustment of the network model, and storing the final network model for actual prediction. According to the method, historical heat supply data, weather conditions, date types and other influence factors serve as input of the model, the predicted value is used for reversely predicting input sequence data, the time sequence correlation between the predicted value and historical heat supply energy consumption data is enhanced, and the model can more effectively capture the deep relation between the data.

Description

technical field [0001] The invention relates to the technical field of smart heating, in particular to a method for predicting heating energy consumption cycles based on generative confrontation networks. Background technique [0002] As one of the main areas responsible for carbon emissions in the building sector, the energy saving and emission reduction of building energy consumption has attracted much attention. About 65% of building energy consumption is energy consumption for heating and air conditioning, and there is obvious room for optimization of heating energy consumption in my country. In the north of my country, most buildings use central heating, which requires precise heating plans. Too high will lead to waste of resources, while too low will fail to meet the daily needs of residents. Therefore, it is necessary to accurately predict the energy consumption of building heating, so as to optimize the design and intelligent control of the overall heating system. ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a heating energy consumption cycle prediction method based on a generative confrontation network to overcome the problem of poor prediction accuracy caused by the inability of existing methods to capture the nonlinear and fluctuating changes in energy consumption data

Images