CNN-LSTM-based building energy consumption prediction method and system

Abstract

The invention provides a CNN-LSTM-based building energy consumption prediction method and system, and the method comprises the steps of employing building energy consumption sequence data obtained by a building energy consumption collection module and data of related influence factors as a data basis, carrying out the preprocessing of the data, and reconstituting a data format needed by a training algorithm; setting a convolutional neural network (CNN) as a feature extraction layer, adopting a structure in which one-dimensional convolution is performed in a feature direction, and then modeling the time sequence of data by using a long short-term memory (LSTM) network; and obtaining a predicted value of the building energy consumption through the model and new input data. By using the algorithm provided by the invention, high-precision prediction of building energy consumption can be realized, and a reference value is provided for optimization of building operation.

Description

technical field [0001] The present invention relates to the technical field of building energy intelligence, in particular, to a method and system for predicting building energy consumption based on CNN-LSTM, especially a method for modeling and predicting building energy consumption using deep learning in machine learning . Background technique [0002] Energy saving and emission reduction in the building field is a necessary part of promoting the construction of ecological civilization. As an important means to grasp the operating characteristics of buildings, building energy consumption prediction has positive significance for building energy saving management and improving building energy utilization. In recent years, the development of big data and artificial intelligence technology has provided data basis and algorithms for modeling and analysis for the prediction of building energy consumption. Deep learning algorithms in machine learning are applied in different fie...

AI Technical Summary

Problems solved by technology

[0003] The traditional building energy consumption prediction analysis method is a physical modeling method based on heat transfer analysis, relying on simulation software to simulate building operation to obtain energy consumption, but there are large errors due to the difficulty in obtaining accurate building parameters

Images