Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Ultra-short-term thermal load prediction method for heat exchange station based on long-short-term time sequence network

A time series, load forecasting technology, applied in forecasting, neural learning methods, biological neural network models, etc., can solve problems such as easy loss of long-term information

Pending Publication Date: 2021-06-29
BEIJING UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that neural networks tend to lose longer-term information when processing long-term sequence information, the present invention provides a Long Short-term Time-series Network (LSTNet) model to deal with this problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Ultra-short-term thermal load prediction method for heat exchange station based on long-short-term time sequence network
  • Ultra-short-term thermal load prediction method for heat exchange station based on long-short-term time sequence network
  • Ultra-short-term thermal load prediction method for heat exchange station based on long-short-term time sequence network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The technical scheme of the present invention will be described in detail below in conjunction with the drawings and specific embodiments of the present invention, so as to make the technical features and advantages of the invention more obvious.

[0024] S1 Select as many relevant characteristic variable data as possible, which may include meteorological data, operating condition data and heat load data, etc., to construct a heat load data set, and obtain X n ={x 1 ,x 2 ,...,x n}, where n is the number of feature variables;

[0025] After S2 constructs the data set, it preprocesses the data:

[0026] S201 compensates the missing value, that is, the value whose data is 0 or empty, and uses the following formula to calculate:

[0027] x i =0.4x i-1 +0.4x i+1 +0.2x i+2 (1)

[0028] where x i is the current missing value, x i-1 、x i+1 and x i+2 Respectively, the values ​​of the previous moment, the next moment, and the next second moment;

[0029] S202 For o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for predicting the ultra-short-term thermal load of a heat exchange station. Firstly, a random forest algorithm is utilized to perform screening and dimension reduction on features; carrying out standardization processing on the data; secondly, a thermal load prediction model based on a long and short term time sequence network is established, the model captures long and short term feature information through a convolution layer and a circulation layer, then the concept of a circulation jump layer is introduced, longer-term feature information is captured. Meanwhile, the linear processing capacity is added for the model through an autoregression algorithm, and the robustness of the model is enhanced. According to the method, the problem of information loss when the neural network processes the long sequence data is solved by utilizing the periodic characteristics of the hourly load, so that the model prediction performance is improved.

Description

technical field [0001] The invention relates to the technical field of central heating, in particular to a method for super-short-term heat load prediction of a heat exchange station. The invention is based on the specific application of the data-driven method in the field of heat load forecasting in the central heating process. Background technique [0002] With the continuous development of China's economy and society, and the continuous improvement of the level of urbanization, central heating is gradually covered in cities and rural areas in northern China. According to the National Bureau of Statistics, as of 2018, the central heating area of ​​my country's cities has reached 8.78 billion square meters, an increase of 5.67% compared with the end of 2017. Fossil fuels consumed by central heating will cause serious environmental pollution and smog. In order to achieve energy conservation and environmental protection, and avoid uneven heating, heat load prediction has bec...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08G06Q10/04
CPCG06N3/084G06Q10/04G06N3/044G06N3/045G06F18/24323G06F18/214
Inventor 刘旭东李硕范青武
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com