Grouping method in wind power plant based on extreme gradient dynamic density clustering

A technology of density clustering and wind farms, applied in the direction of instruments, complex mathematical operations, calculation models, etc., can solve the impact of the correlation redundancy between variables on the clustering effect, the unit information is not fully mined, and the dynamic response time is different, etc. problem, to achieve low sensitivity to noise, increase model complexity, and improve simplification and accuracy

Inactive Publication Date: 2021-03-30
NORTHEAST DIANLI UNIVERSITY +2
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1. When only the mechanical characteristic index is selected, the large inertial time constant affects the accuracy; the single use of the electrical index also has the problem of too single perspective
When the mechanical and electrical indicators are selected at the same time, the effectiveness of the clustering results is improved, but the subjective selection of the clustering indicators may cause the unit information represented by the cluster data to not be fully exploited, and the correlation between variables and data redundancy Sex also has a great influence on the grouping effect;
[0006] 2. The processing speed of the clustering method is fast, but it is easily affected by the shape of the data set, noise data, initial operating point, etc., and the different wind speeds of the wind turbines in the wind farm will lead to different dynamic response times, which cannot be solved simply by relying on distance and density The problem of misalignment of time series

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
  • Grouping method in wind power plant based on extreme gradient dynamic density clustering
  • Grouping method in wind power plant based on extreme gradient dynamic density clustering
  • Grouping method in wind power plant based on extreme gradient dynamic density clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] To establish an equivalent model of a wind farm that accurately characterizes operating characteristics, see figure 1 , the embodiment of the present invention proposes a clustering method in a wind farm based on extreme gradient dynamic density clustering, see the following description for details:

[0039] Step 101: Select the indicators grouped in the wind farm, and perform outlier detection and outlier truncation processing on the corresponding indicator data in a certain period of time;

[0040] Step 102: For the preprocessed grouping index data, use XGBoost to perform dimensionality reduction selection on the grouping index data;

[0041] Step 103: For the selected index data, the clustering method based on DBSCAN-DTW is used to divide the fleet.

[0042] In summary, the embodiment of the present invention can process multi-dimensional time-series characteristic operating data of wind turbines based on the above steps 101 to 103, so as to obtain an accurate and e...

Embodiment 2

[0044] Combine below Figure 1-Figure 5 , specific calculation formulas, examples further introduce the scheme in embodiment 1, see the following description for details:

[0045] 201: Data outlier detection and processing;

[0046]Among them, 13 wind farm grouping indicators are selected, including: rotor angular velocity wr, pitch angle Pitch, electromagnetic torque Tem, mechanical torque Tm of each wind turbine, four mechanical characteristic indicators, stator voltage Vs, active power P, Reactive power Q, rotor voltage d-axis component Vrd, rotor voltage q-axis component Vrq, stator current d-axis component Isd, stator current q-axis component Isq, rotor current d-axis component Ird, rotor current q-axis component Irq characteristic index. Considering the actual engineering conditions such as measurement errors, there are many outliers in the initial data set of the wind farm, which will cause the overall deviation of the subsequent grouping results. The box plot of eac...

Embodiment 3

[0124] Below in conjunction with specific experiments, calculation examples, Table 1-Table 3, the schemes in Embodiments 1 and 2 are verified for feasibility, see the following description for details: the embodiment of the present invention utilizes the matlab / simulink simulation platform to build 16 sets of rated power A wind farm composed of 1.5MW DFIG, such as Image 6 shown. The terminal voltage of DFIG is 690V, which is boosted to 35kV on site by the unit wiring method of one machine, one variable, and then transmitted to the 35kV / 220kV substation through overhead lines and then to the external power grid. The initial wind speed data of the fan is shown in the table below.

[0125] Table 1 Initial wind speed

[0126]

[0127]

[0128] In terms of software configuration, this example uses sklearn machine learning library, vim integrated development editor and anaconda environment management software, which are suitable for writing python code.

[0129] Set a three...

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 grouping method in a wind power plant based on extreme gradient dynamic density clustering, and the method comprises the steps: selecting indexes of grouping in the wind power plant, and carrying out the abnormal value detection and truncation of corresponding index data in a certain time period; for the preprocessed grouping index data, carrying out dimension reduction selection on the grouping index data by adopting XGBoost; and carrying out cluster division on the selected index data on the basis of DBSCAN-DTW clustering. According to the method, the problem of partial missing of actual wind power plant data can be effectively solved, and the model accuracy is improved; and the method is used for processing the multi-dimensional time sequence characteristic operation data of the fan, so that accurate and effective division of the groups in the wind power plant can be obtained.

Description

technical field [0001] The invention relates to the field of grouping in a new energy plant of a power system, in particular to a grouping method in a wind farm based on extreme gradient dynamic density clustering. Background technique [0002] The scale of wind farms is gradually increasing, and its dynamic characteristics have a great impact on the stability of the power system. It is necessary to build a simulation model that accurately reflects the dynamic characteristics of wind farms. If each wind turbine is modeled in detail, the model structure is complex and the dimension is high, which increases the complexity of the power system and the required simulation time. How to establish a wind farm equivalent model that accurately characterizes the operating characteristics plays an important role in the analysis of the safe and stable operation of the system after large wind farms are connected to the grid, and grouping is a key step in wind farm equivalence. [0003] C...

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): G06Q50/06G06Q10/06G06N3/00G06F17/15
CPCG06Q50/06G06Q10/06393G06N3/006G06F17/15
Inventor 王长江陈厚合姜涛李雪李国庆范维段方维
Owner NORTHEAST DIANLI UNIVERSITY
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