Building cold and hot load prediction method based on data-driven Gaussian learning technology

Abstract

The invention relates to a building cold and hot load prediction method based on a data-driven Gaussian learning technology. The method comprises the following steps of S1, obtaining a data set of building cold and hot loads and a plurality of characteristic data sets influencing the cold and hot loads; s2, performing data processing on the trained data set by using a principal component analysismethod, and extracting a set number of principal components; s3, constructing a Gaussian regression process prediction model of the building cold and hot loads, training the constructed Gaussian regression process prediction model based on the training set data so as to achieve the purpose of optimizing the model, and giving a prediction estimation interval in a final prediction model result; andS4, based on the data set after principal component analysis and by adopting the optimized Gaussian process model, predicting the building cold and hot loads and giving a prediction estimation interval. Compared with the prior art, the method has the advantages of being capable of achieving accurate prediction and the like.

Description

technical field [0001] The invention relates to the field of building energy conservation, in particular to a method for predicting building cooling and heating loads based on data-driven Gaussian learning technology. Background technique [0002] Building energy consumption has always been one of the major topics in the field of building energy conservation. Scientific analysis and reasonable prediction of building energy consumption can effectively implement the development concept of building energy conservation. The cooling and heating load of a building occupies a large part of the building load, and the accurate prediction of the building's cooling and heating load is of great significance for energy consumption regulation and the implementation of energy-saving schemes. [0003] Building cooling and heating loads are affected by many factors and have a nonlinear relationship. Existing forecasting technologies generally use algorithmic models such as neural networks or...

AI Technical Summary

Problems solved by technology

[0003] Building cooling and heating loads are affected by many factors and have a nonlinear relationship. Existing forecasting technologies generally use algorithmic models such as neural networks or support vector machines. These models generally have problems such as complex implementation, large amount of calculation, and low prediction accuracy.

Images