Central air conditioner energy consumption forecasting method based on operation data

Abstract

The invention provides a central air conditioner energy consumption forecasting method based on operation data, and belongs to the field of central air conditioner modeling research. Aiming at the highly non-linear central air conditioner modeling problem which is difficult to solve through a traditional mechanism analysis method and a system identification method, central air conditioner energy consumption is forecasted through a method combining a Boruta feature selection method with a BP neural network. The operation data is subjected to energy consumption feature selection through the Boruta feature selection method at first, an energy consumption feature subset is obtained, the energy consumption feature dimension of the operation data is reduced, and then, the redundancy rate of theenergy consumption feature subset is decreased through a pearson correlation coefficient method; and finally, the energy consumption feature subset serves as input of a BP neural network energy consumption model, the central air conditioner system total power serves output of the BP neural network energy consumption model, and a training BP neural network energy consumption forecasting model is reliable and pervasive and has important significance to energy saving strategy implementation.

Description

technical field [0001] The invention belongs to the research field of central air-conditioning modeling, in particular to a method for predicting energy consumption of central air-conditioning based on operating data. Background technique [0002] In the field of central air-conditioning modeling research, previous research work often started from the establishment of a mathematical model of the energy efficiency of the central air-conditioning system, identified the data model parameters of each device based on the system operating data, and finally determined the optimal simulation control strategy for the central air-conditioning system. Here we will This method is called the conventional method. Since the central air-conditioning system is an interconnected and interrelated operation, its energy efficiency mathematical model and identification model have complex structures, and the model parameters are difficult to obtain, and the mechanism modeling of conventional metho...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of the lack of a universal central air-conditioning energy consumption prediction method in the prior art, the present invention proposes a central air-conditioning energy consumption prediction method based on operating data

Images