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

Power system robust state estimation method and system based on deep learning

A state estimation and power system technology, applied in computing, electrical digital data processing, design optimization/simulation, etc., can solve problems such as poor timeliness and low prediction accuracy, and achieve the effects of reducing influence, improving filtering effect, and improving accuracy

Pending Publication Date: 2022-02-08
STATE GRID SHANDONG ELECTRIC POWER
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the deficiencies of the existing technology, the present invention provides a method and system for robust state estimation of power systems based on deep learning, which overcomes the problems of non-Gaussian noise, low prediction accuracy and poor timeliness in the measurement of power system state estimation , which improves the accuracy of the robust state estimation

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 system robust state estimation method and system based on deep learning
  • Power system robust state estimation method and system based on deep learning
  • Power system robust state estimation method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Such as figure 1 and figure 2 As shown, Embodiment 1 of the present invention provides a robust state estimation method for power systems based on deep learning, including the following steps:

[0040] Step S1: Historical data training, learning input historical data based on ATT-CNN-LSTM and KRRSE models, establishing and saving prediction and filtering models.

[0041] Step S2: Determine the abnormal and missing data. For the measurement data of node n, the SVM classification is used to judge whether there is missing or abnormal data in the data set, including:

[0042] Step S201: When the SVM determines that the data is normal, import the data into the KRRSE filter model saved in step S1, process the data and export the state estimation result;

[0043] Step S202: When the SVM determines that the data is missing or abnormal, import the data into the ATT-CNN-LSTM model pre-built in step S1 for fast prediction, and output the estimation result.

[0044] Specificall...

Embodiment 2

[0151] Embodiment 2 of the present invention provides a robust state estimation system for power systems based on deep learning, including:

[0152] The data acquisition module is configured to: acquire the operating parameter data of the power system;

[0153] The data judging module is configured to: judge the abnormality and / or absence of the acquired operation parameter data;

[0154] The first estimation module is configured to: obtain a robust state estimation result according to the obtained operating parameter data and the kernel ridge regression model when there is an abnormality and / or absence;

[0155] The second estimation module is configured to: when there is an abnormality and / or loss, the convolutional neural network of the attention mechanism is used to perform weight screening on the operating parameter data, and a robust state estimation result is obtained according to the long-short-term memory neural network.

[0156] The working method of the system is t...

Embodiment 3

[0158] Embodiment 3 of the present invention provides a computer-readable storage medium, on which a program is stored. When the program is executed by a processor, the method for robust state estimation of a power system based on deep learning as described in Embodiment 1 of the present invention is implemented. A step of.

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 provides a power system robust state estimation method and system based on deep learning. The method comprises the following steps: acquiring operation parameter data of a power system; carrying out abnormity and / or missing judgment on the acquired operation parameter data; when abnormity and / or missing exist, acquiring a robust state estimation result according to the obtained operation parameter data and a kernel ridge regression model; when abnormity and / or deficiency exist, using a convolutional neural network of an attention mechanism to carry out weight screening on the operation parameter data, and acquiring a robust state estimation result according to a long-short-term memory neural network; the problems of non-Gaussian noise, low prediction precision and poor timeliness in quantity measurement in power system state estimation are solved, and the accuracy of robust state estimation is improved.

Description

technical field [0001] The present invention relates to the technical field of power system state estimation, in particular to a method and system for robust state estimation of power systems based on deep learning. Background technique [0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art. [0003] Power system state estimation is the core component of the energy management system. It provides accurate and reliable real-time information on the system state, which plays a vital role in the safe and economical operation of the power system. [0004] At present, the main power system state estimation methods include static state estimation (Static State Estimation, SSE), dynamic state estimation (Dynamic State Estimation, DSE), tracking state estimation (Tracking State Estimation, TSE) and forecasting assisted state estimation (Forecasting-Aided State Estimation, FASE). Among them, F...

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): G06F30/27G06Q50/06G06F119/02
CPCG06F30/27G06Q50/06G06F2119/02
Inventor 张心怡盖午阳张玉敏吉兴权王泽张小龙赵祥君张子衿陈磊盛吉正李冰朱晓晔张婷婷白建勋白志轩张川张琰李佳奇张桂韬郎一凡
Owner STATE GRID SHANDONG ELECTRIC POWER
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