BP neural network heating system energy consumption prediction method based on similar sample screening

Abstract

The invention discloses a BP neural network heating system energy consumption prediction method based on similar sample screening. The method comprises the following steps successively: constructing an initial training sample set A, screening main influence factors, and constructing a training sample set; constructing an influence factor matrix B, calculating a comprehensive similarity coefficient, and screening similar sample subsets; and constructing a final training sample set; predicting energy consumption of heating system of building by utilizing BP neural network. According to the method, the problem that a traditional BP neural network heating system is low in energy consumption prediction precision is solved, the method is simple, the process is easy to calculate, the accuracy ishigh, and engineering personnel can master and learn the energy consumption easily; the method is suitable for predicting the energy consumption of the heating system of the building.

Description

technical field [0001] The invention belongs to the field of energy consumption prediction of heating systems, and in particular relates to a BP neural network energy consumption prediction method for heating systems based on similar sample screening. Background technique [0002] In recent years, the proportion of my country's building energy consumption in the total energy consumption of the society has continued to increase. Among them, the energy consumption of HVAC systems accounts for as high as 40-60% of the entire building energy consumption, making it a "big household" of building energy consumption. Improving the energy efficiency of the HVAC system and reducing the energy consumption of the HVAC system are of great significance to improving the current situation of building energy consumption. How to not only ensure the comfort requirements of indoor personnel, but also reduce building energy consumption has been a long-term focus of scientific research workers an...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a BP neural network heating system energy consumption prediction method based on similar sample screening. This method overcomes the problem of low energy consumption prediction accuracy of the traditional BP neural network heating system. The method is simple and the process is easy. Calculation, high accuracy, easy for engineers to master and learn

Images