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

A Clustering Method for Energy Internet Based on Regional Symmetry

A technology of energy Internet and clustering method, which is applied in the field of object clustering, can solve problems such as difficulty in ensuring the stability and continuity of power generation, and achieve the effects of improving product marketing efficiency, predictability, and smooth operation

Active Publication Date: 2020-10-02
SICHUAN HUATAI ELECTRIC
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

An obvious shortcoming of distributed renewable energy power generation is that it is difficult to guarantee the stability and continuity of power generation; the Energy Internet, which is mainly characterized by extensive access to distributed energy sources, its stable and efficient operation is based on the characteristics of power production and consumption. Based on a precise understanding

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
  • A Clustering Method for Energy Internet Based on Regional Symmetry
  • A Clustering Method for Energy Internet Based on Regional Symmetry
  • A Clustering Method for Energy Internet Based on Regional Symmetry

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0016] figure 1 A schematic flow chart showing an exemplary embodiment of the energy internet clustering method based on regional symmetry of the present invention.

[0017] In an exemplary embodiment of the present invention, as figure 1 As shown, the energy internet clustering method based on regional symmetry may include the following steps:

[0018] Step 1: Obtain the Energy Internet objects to be clustered, and set the range of clustering numbers.

[0019] Specifically, the Energy Internet objects to be clustered with two-dimensional attributes are obtained. The Energy Internet objects to be clustered may be energy production nodes and / or consumption nodes, management nodes, etc. of the Energy Internet. For the Energy Internet objects to be clustered with attribute dimensions exceeding two dimensions, dimensionality reduction can be carried out by means of principal component analysis to reduce them to two-dimensional attributes. For example, in the method of this emb...

Embodiment 2

[0043]In another exemplary embodiment of the present invention, the energy internet clustering method based on regional symmetry can adopt step 1 and step 2 of the above exemplary embodiment to obtain multiple clustering results; then through the following steps 3' and Step 4' realizes energy internet clustering based on regional symmetry.

[0044] Step 3': Comprehensively consider the regional symmetry and other judgment attributes to determine the target number of clusters.

[0045] For the multiple clustering results obtained in step 2, each clustering result corresponds to a known number of clusters and a region symmetry to be determined (for example, an overall symmetry index). For each clustering result, regional symmetry can be determined computationally. Specifically, for each clustering result, the normalized distance between the average value of the one-dimensional attribute of the clustering result and the median value of the dimension attribute can be used as the ...

Embodiment 3

[0053] In this exemplary embodiment, the energy internet clustering method based on regional symmetry assumes that the clustering objects are located in a two-dimensional plane, that is, the clustering is performed based on the two-dimensional attribute values ​​of the objects. For objects with multi-dimensional attributes, the principal component analysis method can be used to reduce the dimensionality before clustering processing, so that the method of this embodiment can be easily extended to multi-dimensional attribute clustering processing.

[0054] Then, the range of the number of clusters can be set, such as 2 to N, according to the estimation of the actual performance requirements of the system.

[0055] Next, pre-cluster each cluster number with the k-means clustering algorithm. The k-means clustering process may include initial position selection, center position calculation, and clustering range calculation and iteration processes. When the iteration converges or re...

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 present invention provides an Energy Internet clustering method based on regional symmetry. The method includes: obtaining energy Internet objects to be clustered with two-dimensional attributes, setting the range of cluster numbers; Pre-clustering the Energy Internet objects to be clustered by a number of clusters respectively, and correspondingly obtaining multiple clustering results; calculating the regional symmetry corresponding to the multiple clustering results, and determining the target clustering according to the regional symmetry number; the target clustering number and the clustering results under the target clustering number are taken as the final clustering result. The present invention can obtain clustering results with more symmetrical attribute distribution through clustering combined with regional symmetry, which is conducive to the realization of self-adaptive and efficient clustering, and also improves the accuracy and suitability of clustering; The typical patterns of user production or consumption are extracted, which improves the predictability of user energy production and consumption, thereby laying the foundation for subsequent analysis and strategy generation.

Description

technical field [0001] The invention relates to the fields of energy production, transmission and consumption, in particular to an object clustering method widely used in the process of energy Internet power production, management and consumption. Background technique [0002] As the most advanced energy system at present, Energy Internet is based on ubiquitous and efficient information and communication infrastructure and open and shared Internet concept, combined with Internet of Things technology and cyber-physical fusion system, it can realize the overall coordination of source-network-load-storage , and through energy cascade utilization and multi-energy complementarity, maximize energy utilization efficiency, greatly reduce energy production and consumption costs, promote environmental protection and reduce exhaust emissions, and provide a solid energy guarantee for the harmonious development of society and the happy life of human beings. [0003] According to the deve...

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 Patents(China)
IPC IPC(8): G06Q10/06G06Q10/04G06Q50/06G06K9/62
CPCG06Q10/06393G06Q10/04G06Q50/06G06F18/23
Inventor 谢伟明阳阳曹军威杨洁黄旭东
Owner SICHUAN HUATAI ELECTRIC
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