Central air conditioning system cooling load prediction method based on SVR algorithm

Abstract

The invention discloses a central air conditioning system cooling load prediction method based on an SVR algorithm. The central air conditioning system cooling load prediction method comprises the steps that a cooling load prediction cycle tau is determined; a dataset with historical data of outdoor meteorological parameters and indoor air conditioning system relevant parameters as a cooling loadprediction calculation model is built; a cooling load prediction training dataset is built; an input dataset and a training set are built; and a prediction model is generated and saved. Indoor coolingload needs in the future time are predicted according to real-time data of the outdoor meteorological parameters and indoor central air conditioning operation parameters, air conditioning cooling load prediction is conducted through the SVR regression algorithm based on an RBF kernel, the training dataset is selected optimally through a PCA (principal component analysis) method, and the needs forthe air conditioning cooling load in a room in the future time are predicted with a high accuracy degree on the basis of a small number of training data through a method with simple model training.

Description

technical field [0001] The invention relates to the technical field of central air-conditioning energy consumption control, in particular to a cooling load prediction method for a central air-conditioning system based on an SVR algorithm. Background technique [0002] With the development of society and economy, the energy consumption of buildings has increased year by year, accounting for about 40% of the global energy demand. As far as our country is concerned, building energy consumption accounts for as high as 30% of the whole society's energy consumption. At the same time, air conditioning and heating systems account for about half of the total building energy consumption, and the proportion has been increasing in recent years. It is less than 10%, so the energy-saving space of central air-conditioning system is fully exploited, and the energy-saving of air-conditioning system is the key task of building energy conservation. [0003] At present, the design of the centr...

AI Technical Summary

Problems solved by technology

[0013] In view of this, the problem to be solved by the present invention is to provide a method for forecasting the cooling load of a central air-conditioning system based on the SVR algorithm for problems such as complex models and difficult application in the prior art.

Images