A power system dynamic safety confidence evaluation method based on an integrated learning scheme

A power system and integrated learning technology, applied in integrated learning, instruments, data processing applications, etc., can solve problems such as weak robustness and generalization ability, weakening DSA strength, classification or prediction errors and inaccurate DSA results, etc. Achieve the effect of enhancing the robustness and generalization ability of the system, improving the stability of the system structure, and benefiting the stability of the model structure

Pending Publication Date: 2019-05-31
CHINA THREE GORGES UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these advanced data mining methods have some limitations: ①The cumbersome adjustment procedure prolongs the training time, which cannot prevent very fast dynamic unsafe propagation, which weakens the strength of their online DSA; ②The prior information in the tra...

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 system dynamic safety confidence evaluation method based on an integrated learning scheme
  • A power system dynamic safety confidence evaluation method based on an integrated learning scheme
  • A power system dynamic safety confidence evaluation method based on an integrated learning scheme

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0111] Table 1 describes the system calculation time and performance table obtained by testing the present invention on the IEEE-50 computer system. The system consists of 50 generators, 145 nodes and 453 branches. In the following test, 200 ELMs are used and corresponding parameters are set, 3000 samples and 30 features are randomly selected, the credibility estimation parameter is set to 40, 20% of the database is randomly selected as the test data, and the rest as training data. Consider a single contingency case first, and test multiple contingency cases last. The average training and testing time of a single ELM during validation is only 1.54 seconds and 0.0313 seconds, respectively. IS is fully tested and shown, as shown in Table 1: the confidence is 93.85%, and the accuracy is 100%, that is, 1191 out of 1269 instances can be reliably determined by IS, and their classification is 100% correct, which means IS can detect potential misclassification very well.

[0112] ...

experiment example 2

[0116] Table 2 tests the calculation time and performance of the dynamic equivalent system of China's real-world power grid. There are 39 motors, 120 load nodes, 223 AC lines and 4 high-voltage DC transmission lines. In this test, 784 operation samples and 196 candidate features are selected, 20% of the database is randomly selected as test data, and the rest are used as training data. There are 157 test instances and 627 training instances respectively, and the training data are used to adjust Single ELM. Finally, the comprehensive test results are shown in Table 2, which also confirms the Figure 5 As shown by the regularity, IS can well identify prediction errors.

[0117] Table 2

[0118]

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

A power system dynamic safety confidence evaluation method based on an integrated learning scheme comprises the steps that firstly, feature automatic sorting is conducted on input feature full-set data, so that feature selection of the next stage is facilitated, and a high-quality training set is provided for sample training; independent extreme learning machine (ELM) training is carried out on the sample set, and finally, model fitting is carried out on the trained ELM to achieve integrated learning, thereby obtaining reliable information. The method is beneficial to the unique property of ELM; training and decision rules are strategically designed; an intelligent system (ISS) can learn and work quickly, potential risks can be recognized, and the method and the device have very importantsignificance in providing effective evaluation on the credibility of dynamic security assessment (Dynamic Assertion, DSA) results.

Description

technical field [0001] The invention relates to the field of power system dynamic security, in particular to a power system dynamic security confidence evaluation method based on an integrated learning scheme. Background technique [0002] In recent years, with the complexity of the power system structure and the research and construction of smart grids, it has become the focus of attention of countries all over the world. According to my country's basic national conditions, the development strategy of building a strong, reliable, economically efficient, clean and environmentally friendly, transparent and open, friendly and interactive unified strong smart grid is proposed. The smart distribution network is one of the key links of the smart grid, and the risk assessment of the smart grid is an important guarantee for realizing the overall construction goal of the smart grid. How to comprehensively plan the key risk assessment indicators of the smart distribution network, an...

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): G06Q10/06G06Q50/06G06N20/20
Inventor 刘颂凯毛丹史若原刘礼煌佘小莉杨楠王丰李世春
Owner CHINA THREE GORGES UNIV
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