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

Power load clustering method and system

A technology of power load and clustering method, applied in instruments, character and pattern recognition, data processing applications, etc., can solve the problems of incomplete time period, reduced computing efficiency, performance, time series data noise, etc., and achieve strong robustness , the effect of retaining the characteristics of load data

Pending Publication Date: 2020-03-24
CHINA ELECTRIC POWER RES INST +1
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method based on the original data is to directly cluster the data. This method is simple but has many limitations: if the sampling time interval of the time series is required to be equal, the processing effect on the noise is not good, and it will be caused by the disaster of dimensionality of the data. Reduce computational efficiency, performance
[0006] In the process of collecting user load data, first of all, the collection of single user load data will face situations such as missing data and incomplete time periods, and the robustness of the existing load clustering algorithm does not meet the requirements; secondly, multiple users The collection time of load data is not synchronized and the length of time is not equal, and the commonly used feature-based clustering method will limit the load of the user group to be within the same period
In addition, due to the noise in the time series data itself or for encryption purposes, the clustering results obtained by the existing load clustering methods are not unique

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
  • Power load clustering method and system
  • Power load clustering method and system
  • Power load clustering method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] Such as figure 1 As shown, a kind of power load clustering method provided by the present invention includes:

[0060] S1. Obtain the load time series of each user, and insert a phase shift into the load time series of each user to obtain an embedded sequence;

[0061] S2. Using a linear neural regression method for the embedded sequence to generate mapping function parameters;

[0062] S3. Using the similarity of the mapping function parameters of each user to cluster the users to obtain a typical load curve.

[0063] pass figure 2 The power load clustering method provided by the present invention is specifically described, including:

[0064] Step 1. Collect the load time series data of a certain amount of power users. The collection periods of these data overlap but not completely overlap, the time length is different, and there is certain noise.

[0065] Step 2. Insert a phase shift into the load time series of each user, so that each moment of the load time se...

Embodiment 2

[0086] Based on the same inventive concept, an embodiment of the present invention also provides a power load clustering system, including:

[0087] The insertion module is used to obtain the load time series of each user, and insert a phase shift into the load time series of each user to obtain an embedded sequence;

[0088] A generation module for generating mapping function parameters using a linear neural regression method for the embedded sequence;

[0089] The clustering module is used to cluster the users by utilizing the similarity of the mapping function parameters of each user to obtain a typical load curve.

[0090] In an embodiment, the generating module includes:

[0091] An optimization unit is used to optimize the embedding dimension and delay amount of the embedding sequence by using Shannon entropy;

[0092] conversion unit for the entire time period T n , the embedding sequence is transformed into T n - a matrix of mτ+1 rows and m columns;

[0093] A map...

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 power load clustering method and system. The power load clustering method comprises the steps: obtaining a load time sequence of each user, inserting a phase shift into the load time sequence of each user, and obtaining an embedded sequence; generating mapping function parameters for the embedded sequence by adopting a linear neural regression method; and clustering the users by utilizing the similarity of the mapping function parameters of the users to obtain a typical load curve. According to the power load clustering method, load time series data with asynchronousacquisition time, unequal time lengths and noise can be processed.

Description

technical field [0001] The invention relates to the field of electric power system automation, in particular to an electric load clustering method and system. Background technique [0002] The clustering of power users based on load data can solve the problem of fair market segmentation, for example: load clustering can explore building energy patterns, or provide reference for time-of-use electricity pricing strategies. The typical load curve of a certain type of user is usually obtained by averaging all measured load curves in the same cluster, so effective clustering of power users based on load data is the key. [0003] At present, there are three main types of data clustering methods commonly used at home and abroad: one is the method based on original data; the other is the method based on feature extraction; the other is the method based on the model. The method based on the original data is to directly cluster the data. This method is simple but has many limitations...

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): G06Q10/06G06Q50/06G06K9/62
CPCG06Q10/0639G06Q50/06G06F18/23
Inventor 钱甜甜王珂石飞刘建涛王礼文郭晓蕊王刚李亚平周竞徐鹏毛文博朱克东
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

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