Air conditioner load prediction method and system

Abstract

The invention relates to an air conditioner load prediction method and system.The method comprises the steps of acquiring a sample set, dividing data of the sample set into a training data set and a prediction data set, wherein the sample set at least comprises sample data and label data corresponding to the sample data; extracting influence factors in the sample data, and screening a plurality of characteristic indexes from the influence factors as an input sequence by adopting grey correlation analysis; obtaining a basic model, wherein the basic model comprises a bidirectional LSTM model and a bidirectional GRU model which are arranged in sequence; inputting a corresponding input sequence in the training data set into the basic model for training to obtain a prediction model; and inputting a corresponding input sequence in the prediction data set into the trained prediction model for load prediction to obtain a predicted value of the air conditioner load. Effective dimensionality reduction is performed on a large amount of data by adopting grey correlation analysis, and the selected basic model is matched, so that the prediction precision can be improved, and the training time can be shortened.

Description

technical field [0001] The invention relates to the technical field of building energy conservation, in particular to an air-conditioning load forecasting method and system. Background technique [0002] In the energy consumption of the whole society, building energy consumption has become a major component, while HVAC energy consumption accounts for 68% of building energy consumption. The optimal control of HVAC provides great help in reducing the energy consumption of air-conditioning. Among the many optimal controls, the optimization method based on air-conditioning load forecasting has become a very important field. To give an example, for the start-up control of chillers, the load of the building can be predicted to know the cooling capacity required at the next moment in advance, and the number and running time of chillers can be controlled to achieve energy-saving effects. [0003] For the prediction of air-conditioning load, experts at home and abroad have done a lo...

AI Technical Summary

Problems solved by technology

[0003] For the prediction of air-conditioning load, experts at home and abroad have done a lot of research and proposed many prediction methods of air-conditioning load, including two categories, the first category: linear regression prediction method, time series prediction method, etc., but due to load The essence of forecasting is nonlinear, so although the linear forecasting method is simple, the effect is not good; and because the factors affecting the load are not only the change of the load itself, but also factors such as outdoor conditions, the time series forecasting method is not comprehensive and accurate enough.

The second category: forecasting based on artificial neural network models. Since artificial neural networks can simulate nonlinear problems well, they have been widely used in forecasting. For example, neural networks are used to establish air-conditioning load forecasting models, but this method Slow convergence speed, low algorithm efficiency, prone to overfitting, poor training ability, poor predictive ability, etc. when faced with a large amount of data

Images