Deep learning-based heat exchange station thermal load short-term prediction method and prediction system

Abstract

The invention provides a heat exchange station thermal load short-term prediction method and prediction system based on deep learning. The prediction method comprises the following steps: constructing a real data set and a simulation data set of working condition operation; extracting features in each data set by using a CNN convolutional neural network, and inputting the features into an improved LSTM prediction model for training; and correcting the prediction result of the real data by using the prediction result of the simulation data to obtain a final result. According to the scheme of the invention, a comparison data set is established by combining a real operation historical data set and building energy consumption simulation data, then features are extracted by using a CNN convolutional neural network, and the features are respectively input into an improved LSTM prediction model for training. Then, two prediction models trained by real data and simulation data are used for predicting a current value, and finally, a correction system is used for correcting two output results to obtain a final prediction value. The accuracy of the whole prediction method is improved.

Description

technical field [0001] The present invention relates to the field of heat load prediction of heat exchange stations, in particular, to a short-term heat load prediction method and prediction system for heat exchange stations based on deep learning. Background technique [0002] Central heating equipment is an important basic energy facility to ensure people's production and life. With the continuous advancement of China's urbanization process, the scale of centralized heating in large and medium-sized cities in my country has continued to expand, and the total heating area of ​​a single city has reached tens of millions of square meters or even hundreds of millions of square meters. With the continuous increase of the heating area, the heating system will cause serious environmental pollution and smog. Therefore, in the face of a large and complex heating system, heating companies need to balance the contradictory factors in heating safety goals, reliability, environmental ...

AI Technical Summary

Problems solved by technology

Due to the complexity of the heating system, strong dynamics, large inertia, and obvious user differences, it is difficult to establish an accurate heat load forecasting mechanism model through mathematical modeling methods

Images