Feature extraction method and system for energy consumption prediction

Abstract

The invention relates to the field of central air conditioner energy consumption prediction, discloses a feature extraction method and system for energy consumption prediction, and aims to quickly screen input features of energy consumption prediction and improve the generalization performance of an energy consumption prediction algorithm. The method comprises the steps of collecting historical operation data of a to-be-analyzed central air conditioning system, and preprocessing the historical operation data to obtain an initial feature set; performing training according to the initial featureset to obtain a gradient boosting tree energy consumption prediction model, and calculating the contribution degree of each input feature; performing feature screening according to the contribution degree to obtain an optimized feature set; optimizing the gradient boosting tree energy consumption prediction model according to the optimization feature set, and obtaining a prediction value according to the optimized gradient boosting tree energy consumption prediction model; calculating a mean square error between the contribution degree and the predicted value; and screening the mean square error by adopting a preset feature screening termination condition to obtain an optimal feature set.

Description

technical field [0001] The invention relates to the field of central air-conditioning energy consumption prediction, in particular to a feature extraction method and system for energy consumption prediction. Background technique [0002] The central air-conditioning system is one of the main systems of energy consumption in public buildings, so the research on energy consumption prediction and optimal control methods of the central air-conditioning system has attracted extensive attention. The central air-conditioning system is usually composed of multiple refrigeration units, water pumps, cooling towers and other energy-consuming equipment. Its working status is affected by factors such as user demand, season, and weather, which leads to complex operating data of the central air-conditioning system and difficult analysis of energy consumption changes. and modeling. In order to realize accurate energy consumption prediction of central air-conditioning system, it is necessar...

AI Technical Summary

Problems solved by technology

In the current data-driven central air-conditioning system energy consumption prediction method, most of the processing of input features adopts expert experience and manual screening methods, which have shortcomings such as low efficiency and poor versatility, making the generalization performance of energy consumption prediction weak

In addition, the multi-objective optimization method can also be used to optimize the feature combination, but due to the large number of original features, the optimization time will be very long

Images