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

Multi-source data processing and fusion method and system for low-voltage distribution network

A low-voltage distribution network, multi-source data technology, applied in electrical digital data processing, electrical components, circuit devices, etc., can solve problems such as power grid faults, slow convergence of neural network algorithms, and uncertain network structure, and achieve safe operation. reliable results

Inactive Publication Date: 2021-01-12
GUIZHOU POWER GRID CO LTD
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Using the existing distribution network automation system to directly process and analyze so many distribution network data will occupy a large amount of system resources, and the multi-source data obtained cannot rely on these traditional algorithms for real-time and effective processing. For example, the neural network algorithm used in the low-voltage distribution network has disadvantages such as slow convergence speed, small local poles, and uncertain network structure.
The data in the low-voltage distribution network is affected by many factors, and there are many defects. If the algorithm used cannot handle the multi-source data generated by the power grid in a timely manner, it is very likely that the power grid will be paralyzed and lead to grid failure.

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
  • Multi-source data processing and fusion method and system for low-voltage distribution network
  • Multi-source data processing and fusion method and system for low-voltage distribution network
  • Multi-source data processing and fusion method and system for low-voltage distribution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] refer to Figure 1 to Figure 7 , which is the first embodiment of the present invention, this embodiment provides a low-voltage distribution network multi-source data processing and fusion method, including:

[0039] S1: Obtain multi-source data and divide it using the Map mapping mechanism to obtain sub-datasets of equal capacity.

[0040] Specifically, according to the target requirements, the multi-source data that needs to be collected includes current, voltage, power, etc., and the Map mapping mechanism is used to divide the collection of multi-source data into sub-dataset 1 and sub-dataset 2 according to the equal capacity. . . , sub-data n, and are assigned to each task execution node through the task assignment node.

[0041] Further, dividing the multi-source data also includes the following steps,

[0042] Perform discretization processing on the obtained multi-source data to obtain discretized data; among them, the methods of discretization processing inclu...

Embodiment 2

[0083] refer to Figure 8 ~ Figure 9 , is the second embodiment of the present invention. This embodiment is different from the first embodiment in that it provides a low-voltage distribution network multi-source data processing and fusion system, including:

[0084] The data processing module 100 is used for acquiring multi-source data, and divides the multi-source data through the Map mapping mechanism, and then can establish sub-data sets of equal capacity.

[0085] The optimization module 200 is used for the improvement of the Hermite orthogonal basis neural network algorithm, and is used for establishing it on the Hadoop distributed cluster. The Hermite orthogonal basis neural network algorithm is optimized through the MapReduce parallel model, and a more efficient multi-source data fusion model is given, which can classify and fuse mixed data from different sources and types.

[0086] The training module 300 is connected with the data processing module 100 and the optim...

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 multi-source data processing and fusion method and system for a low-voltage distribution network, and the method comprises the steps: firstly transforming a conventional neural network, proposing a Hermite orthogonal basis forward neural network according to the polynomial interpolation and approximation theory, building an algorithm model based on the Hermite orthogonalbasis forward neural network on the basis, and carrying out multi-source data processing and fusion of the low-voltage distribution network; performing algorithm parallelization under a MapReduce framework so that the real-time processing requirement of the low-voltage power distribution network on mass data can be better met, finally, verifying the model by simulation. The result proves that themodel is higher in low-voltage power distribution network multi-source data processing efficiency and more accurate in result.

Description

technical field [0001] The technical field that the present invention relates to, in particular, relates to a low-voltage distribution network multi-source data processing and fusion method and system. Background technique [0002] In recent years, the number of low-voltage distribution stations has been very large. In the application, it is necessary to measure more than 20 multi-source data such as total / separate phase active and reactive power, current, voltage, apparent load power and power factor in real time. However, the existing The low-voltage distribution network mainly uses traditional algorithm models such as neural network method, Kalman filter method, Bayesian inference method and cluster analysis method for multi-source data processing. [0003] Using the existing distribution network automation system to directly process and analyze so many distribution station data will occupy a large amount of system resources, and the multi-source data obtained cannot rely...

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): G06F30/27G06K9/62G06N3/04H02J3/00G06F113/04
CPCG06F30/27H02J3/00H02J2203/20G06F2113/04G06N3/045G06F18/25G06F18/214
Inventor 冯义徐长宝凌宗洋张腾飞刘明祥孟悦恒刘海姣戴雯菊田昕泽王雷
Owner GUIZHOU POWER GRID CO LTD
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