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

A power grid power supply reliability level clustering method and system

A grid power supply and reliability technology, applied in the field of clustering, can solve problems such as unsatisfactory results and inability to obtain clustering results, and achieve the effects of improving clustering effects, increasing credibility, and reducing dimensions

Pending Publication Date: 2019-06-04
CHINA ELECTRIC POWER RES INST +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The selection of the initial clustering center has a great influence on the clustering results. Once the initial value is not well selected, effective clustering results may not be obtained, which has become a major problem of the K-means algorithm.
To solve this problem, many algorithms use genetic algorithm (GA). For example, in the literature, genetic algorithm (GA) is used for initialization, and internal clustering criteria are used as evaluation indicators, but the effect is not satisfactory.

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 power grid power supply reliability level clustering method and system
  • A power grid power supply reliability level clustering method and system
  • A power grid power supply reliability level clustering method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] In the present invention, the input data is preprocessed, and the significance of the correlation coefficient is checked after the correlation processing. In addition, there is an important step of using other auxiliary methods-using the principal component analysis method for demonstration and discrimination. Then, the optimized cost function is used for clustering, so that the clustering can distinguish the data with small similarity between classes as much as possible. Directly apply the output clustering results without reprocessing the applied data, such as abnormal data, even if the clustering results are good, it is difficult to achieve good results in engineering applications. Therefore, in actual engineering applications, the actual situation or data used should also be discriminated against abnormalities, so that abnormal data will not participate in the calculation of the same category.

[0067] The present invention provides a grid power supply reliability l...

Embodiment 2

[0094]This embodiment is to study how to evaluate the reliability level of the State Grid prefecture-level power supply company. The evaluation content specifically includes two aspects: one is the average power outage time of users; the other is the average number of power outages of users. From the perspective of business analysis, the main factors affecting the reliability of power supply are connection rate, transferable rate, line segmentation rate, ring network rate, cable rate, distribution automation rate, equipment level, etc. However, whether there is a relationship between these factors and how strong the relationship is cannot be analyzed in detail in the business, and auxiliary analysis and judgment are required.

[0095] In this study, the factors that affect the reliability index are selected to establish an index set. After collecting the index set, the abnormal data is processed and corrected. Through business analysis, the prefecture-level power supply compani...

Embodiment 3

[0121] Based on the same inventive idea, the present invention also provides a clustering system based on the K-means algorithm for the reliability level of power grid power supply, its structure diagram is as follows Figure 4 shown, including:

[0122] Building blocks for selecting factors that affect power supply reliability to establish an index set;

[0123] A clustering index determination module, used to determine the final clustering index from the index set by adopting the significance check of the correlation coefficient;

[0124] The clustering analysis module performs clustering analysis on the final clustering index to obtain the optimized clustering index;

[0125] An optimization module, configured to optimize the basic data describing the reliability level of power grid power supply according to the optimized clustering index.

[0126] Further: the clustering index determination module further includes:

[0127] The preprocessing sub-module is used to prepro...

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 relates to a power grid power supply reliability level clustering method and system. The method comprises the steps of selecting factors influencing power supply reliability to establishan index set; Determining a final clustering index from the index set by adopting correlation coefficient significance verification; Performing clustering analysis on the final clustering index to obtain a clustering result of power supply reliability level classification; And optimizing the basic data describing the power supply reliability level according to the clustering result. According tothe method, a series of processing is carried out on the index set before clustering, correlation coefficient significance verification is carried out after data correlation coefficient calculation, and auxiliary judgment, namely principal component analysis, is added, so that the dimension is reduced, and the credibility is also improved to a certain extent.

Description

technical field [0001] The invention relates to a clustering method, in particular to a grid power supply reliability level clustering method and system. Background technique [0002] The K-means algorithm is a hard clustering algorithm, which is a representative of a typical prototype-based objective function clustering method. It uses a certain distance from the data point to the prototype as the optimized objective function, and uses the method of finding the extreme value of the function to obtain an iterative operation. adjustment rules. The K-means algorithm uses the Euclidean distance as the similarity measure, which seeks the optimal classification corresponding to an initial cluster center vector V, so that the evaluation index J is the smallest. The algorithm uses the error sum of squares criterion function as the clustering criterion function. [0003] The K-means algorithm belongs to the unsupervised learning method. This algorithm takes k as a parameter and d...

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): G06K9/62G06Q50/06
Inventor 高波陈红森张鹏呂颖王宏刚芦晶晶于之虹胡建勇
Owner CHINA 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