Energy consumption prediction method and device based on complementary fuzzy neural network

A fuzzy neural network and complementary technology, applied in the field of energy consumption forecasting, can solve problems such as poor reliability of energy consumption data, and achieve the effects of improving accuracy, reducing computational complexity, and improving computational speed.

Active Publication Date: 2016-08-24
西安咸林能源科技有限公司
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The invention provides a method and device for forecasting energy consumption based on complementary fuzzy neural network to solve the problem of poor reliability of energy consumption data predicted by existing energy consumption data prediction schemes

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
  • Energy consumption prediction method and device based on complementary fuzzy neural network
  • Energy consumption prediction method and device based on complementary fuzzy neural network
  • Energy consumption prediction method and device based on complementary fuzzy neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] refer to figure 1 , shows a flow chart of steps of a method for predicting energy consumption based on complementary fuzzy neural network according to Embodiment 1 of the present invention.

[0030] The steps of the method for forecasting energy consumption based on complementary fuzzy neural network in this embodiment include:

[0031] Step S102: Obtain historical energy consumption data corresponding to the energy to be tested.

[0032] The historical data of energy consumption is the data corresponding to the historical usage of the energy. For example, if the energy to be tested is coal, then the historical data of energy consumption is the amount of coal used by the enterprise within a certain period of time. The historical energy consumption data is data related to the historical consumption of the energy to be tested within a certain period of time. For example, the certain period of time can be one month, one week, or three days, etc., which is not specifically...

Embodiment 2

[0054] refer to figure 2 , shows a flowchart of steps of a method for predicting energy consumption based on a complementary fuzzy neural network according to Embodiment 2 of the present invention.

[0055] The specific steps of the method for forecasting energy consumption based on complementary fuzzy neural network in this embodiment include:

[0056] Step S202: Obtain historical energy consumption data corresponding to the energy source to be tested.

[0057] After obtaining the historical energy usage data corresponding to the energy to be tested, the historical energy usage data is classified and regularized through the membership function. Specifically, classify and regularize the energy historical data to form a data domain, denoted by X:

[0058] Taking X as the data universe, the mapping A(x): X→[0,1] determines a fuzzy subset A on X, and A(x) is called the membership function of A, where the membership function is as image 3 shown.

[0059] A(x)∈[0,1] is call...

Embodiment 3

[0112] refer to Figure 4 , shows a structural block diagram of an energy consumption forecasting device based on a complementary fuzzy neural network according to Embodiment 3 of the present invention.

[0113] The energy consumption forecasting device based on complementary fuzzy neural network in this embodiment includes: an acquisition module 302 for acquiring historical energy consumption data corresponding to the energy to be tested; a regularization module 304 for classifying and regularizing the historical energy consumption data ; The screening module 306 is used to gray out the regularized historical data of energy consumption to filter out valid historical data; the normalization module 308 is used to normalize the valid historical data; the fuzzy processing module 310, for performing fuzzy processing on the normalized data; input module 312, for inputting the fuzzy processed data into the fuzzy neural network model, and predicting the fuzzy processed data by the fu...

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 provides an energy consumption prediction method and device based on complementary fuzzy neural network. The method comprises steps of: acquiring energy consumption historical data corresponding to energy to be tested; classifying and structuring the energy consumption historical data; performing gray treatment on the structured energy consumption historical data and screening out valid historical data; normalizing the valid historical data; performing fuzzy processing on the normalized data; inputting the data subjected to the fuzzy processing into the fuzzy neural network which predicts an energy consumption predicted value corresponding to the data subjected to the fuzzy processing; performing anti-normalization processing on the energy consumption predicted value; performing whitening processing on an anti-normalization processing result to obtain and output a target predicted value. The energy consumption prediction method and device based on complementary fuzzy neural network may increase the accuracy of the energy consumption prediction results.

Description

technical field [0001] The invention relates to the technical field of energy consumption forecasting, in particular to an energy consumption forecasting method and device based on a complementary fuzzy neural network. Background technique [0002] In energy management systems and intelligent energy consumption systems, due to sudden changes in energy consumption (coal, natural gas, oil and other energy sources), lack of data statistics, and various factors affecting data, energy consumption data prediction has always been a difficult problem. [0003] At present, the commonly used methods for predicting energy consumption data in large-scale industrial fields are: fuzzy prediction method and artificial neural network method. [0004] Although the fuzzy forecasting method can deal with inaccurate and fuzzy phenomena, the learning ability of this method is poor. It needs to manually select the calculation parameters and determine the membership degree of the historical energy...

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): G06Q10/04G06N7/04
CPCG06N7/046G06Q10/04
Inventor 张定恩杨滨刘宝林李光辉李智滨王修业付家旗
Owner 西安咸林能源科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap