Fast state estimation method for complex nodes and large-scale measurement data

A technology for measuring data and fast state, applied in the field of fast state estimation, to achieve the effect of reducing training time overhead and meeting the requirements of accuracy and real-time performance

Inactive Publication Date: 2011-12-28
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Principal component analysis has certain defects when the data set is highly nonlinear

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
  • Fast state estimation method for complex nodes and large-scale measurement data
  • Fast state estimation method for complex nodes and large-scale measurement data
  • Fast state estimation method for complex nodes and large-scale measurement data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The preferred embodiments will be described in detail below in conjunction with the accompanying drawings. It should be emphasized that the following description is only exemplary and not intended to limit the scope of the invention and its application.

[0039]Under the conditions of large-scale measurement data in complex nodes and high requirements for real-time prediction and accuracy, a good regression training method must consider the impact of the prediction accuracy and space-time complexity that can be achieved by training at the same time. At the same time, it can effectively overcome the adverse effects caused by the sharp drop in training performance caused by the large sample dimension. KMPLM (Kernel Matching Pursuit Learning Machine, Kernel Matching Pursuit Learning Machine) solves the problem of prediction accuracy well, but the time and space complexity of training under large-scale and high-dimensional sample sets is too large. The LLE (Locally Linear ...

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 fast state estimation method suitable for complex nodes and large-scale measurement data in the technical field of power system state estimation. Including: respectively incorporating M measured values ​​at consecutive T times into the measurement set to form an M×T two-dimensional array; performing LLE nonlinear dimensionality reduction on the M×T two-dimensional array; The amplitude and phase angle are respectively sample trained to generate voltage amplitude and phase angle sample models, and use the generated sample model to predict the node voltage amplitude and phase angle; use the Newton-Raphson iterative method to correct the predicted value and obtain the state Estimated value; put the estimated value of the state as the true value of the state at the Tth moment into the state quantity set; take the measurement data of the first T moments up to the T+1th moment, repeat the above steps, and obtain the T+th The state estimation value at time 1 realizes rolling prediction. On the premise of ensuring the prediction accuracy, the present invention realizes fast training of large-scale high-dimensional sample data and prediction of system state quantities.

Description

technical field [0001] The invention belongs to the technical field of power system state estimation, in particular to a fast state estimation method suitable for complex nodes and large-scale measurement data. Background technique [0002] One type of method in power system state estimation is to combine the prediction and estimation iteration of the state quantity of the power system, and find the trajectory of the state variable through the regression of the estimated time series that has been completed, and predict the further change of the state variable. , using the predicted value as the starting point of iterative calculation to complete the estimation of the state quantity. The accuracy of state estimation determines whether the modern power system can accurately and comprehensively grasp the actual operating state of the system; the real-time nature of state estimation determines whether the modern power system can predict and analyze the operating trend of the sys...

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 Patents(China)
IPC IPC(8): G01R31/00G06N1/00G06N99/00
Inventor 李元诚高珂
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
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