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

Building energy consumption prediction method based on long-term and short-term memory network hybrid model

A technology of long-term and short-term memory and building energy consumption, which can be applied to biological neural network models, predictions, neural learning methods, etc., and can solve problems such as accuracy errors

Pending Publication Date: 2020-12-18
STATE GRID LIAONING ELECTRIC POWER RES INST +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] Aiming at the problem that the prediction accuracy of building energy consumption is relatively large, the present invention provides a building energy consumption prediction method based on a long-short-term memory network hybrid model to improve the accuracy and robustness of the prediction

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
  • Building energy consumption prediction method based on long-term and short-term memory network hybrid model
  • Building energy consumption prediction method based on long-term and short-term memory network hybrid model
  • Building energy consumption prediction method based on long-term and short-term memory network hybrid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The specific embodiments of the present invention will be described below with reference to the accompanying drawings, so that those skilled in the art can better understand the present invention.

[0075] figure 1 Unroll the topology map for Simple Recurrent Neural Networks - Real Time.

[0076] Generally, neural network models can be divided into feedforward neural network (FFNN) and recurrent neural network (RNN). FFNNs are widely used to process data in the spatial domain while ignoring data occurrences about time (i.e., temporal information). On the other hand, RNN architectures can be viewed as loop-back architectures with interconnected neurons that can model sequential and temporal dependencies between data on a larger scale [43] .

[0077] The standard for RNN architecture is in figure 1 given in. Each node in the network starts from the current state (x t ) receives input and returns from the previous state (h (t-1) ) receives the hidden state value of ...

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 belongs to the field of control of power demand side response relates to a building energy consumption prediction method based on a long-term and short-term memory network hybrid model,and provides an energy consumption prediction model for a building, and the model adopts a long-term and short-term memory network LSTM and an improved sine and cosine optimization algorithm. Accurateand reliable building energy consumption prediction can be performed, meanwhile, a novel Haar wavelet-based mutation operator is introduced, so that the divergence of the sine and cosine optimizationalgorithm to the global optimal solution is improved. The proposed improved sine and cosine optimization algorithm ISCOA can optimize hyper-parameters (learning rate, weight attenuation, momentum andhidden unit number) of the LSTM. The ISCOALSTM proposed by the method can calculate a stable and accurate prediction result, and further serves as an effective tool for solving a problem of energy consumption prediction.

Description

technical field [0001] The invention relates to the control field of power demand side response, in particular to a building energy consumption prediction method based on a long-short-term memory network hybrid model. Background technique [0002] With the rapid growth of the global population, the development of industrialization, the development of economy, and the development of life and society, these developments have had a significant impact on global energy consumption and the environment. 92% of people live in buildings, increasing the operation of energy-intensive buildings to meet people's living needs and comforts, which account for 80-90% of total energy consumption over the building's life cycle. With buildings accounting for about 39% of global energy consumption and greenhouse gas emissions accounting for about 38% of global emissions, buildings have become the largest consumer of energy. According to the International Energy Outlook 2017, “Electricity is the...

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
IPC IPC(8): G06N3/04G06N3/08G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06G06N3/049G06N3/08G06N3/045
Inventor 李桐王刚崔嘉宋进良杨智斌刘扬任帅杨滢璇杨俊友颜宁
Owner STATE GRID LIAONING ELECTRIC POWER RES INST
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