Power system dynamic frequency response curve prediction method and system based on XGBoost

A frequency response curve and dynamic frequency technology, which is applied in the field of dynamic frequency response curve prediction based on XGBoost power system, can solve the problems of strong dependence on deep learning samples and slow offline training speed, and achieve the goal of reducing dependence and increasing output diversity. Effect

Pending Publication Date: 2022-03-04
ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the deficiencies in the above-mentioned background technology, the present invention proposes a method and system for predicting dynamic frequency response curves of power systems based on XGBoost, which solves the technical problems of strong dependence on deep learning samples and slow offline training speed

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 dynamic frequency response curve prediction method and system based on XGBoost
  • Power system dynamic frequency response curve prediction method and system based on XGBoost
  • Power system dynamic frequency response curve prediction method and system based on XGBoost

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Example 1, such as figure 1 As shown, a method for predicting the dynamic frequency response curve of a power system based on XGBoost, the steps are as follows:

[0045]S1. Obtain a diverse database for offline training based on the simulation results of massive predicted fault scenarios; among them, massive predicted fault scenarios include new energy off-grid faults, large-capacity unit trip faults, and DC blocking faults. The data in the diverse database includes input features and corresponding output dynamic frequency response values, where the input features are unit inertia time constant, unit start-stop status, active power disturbance, fault location, unit regulated power and spinning reserve Level.

[0046] The corresponding output dynamic frequency response value is to use the inertia center frequency to represent the system frequency dynamic response in the global state, and the specific formula is:

[0047]

[0048] where f COI Indicates the center fr...

Embodiment 2

[0099] Embodiment 2, a dynamic frequency response curve prediction system based on XGBoost power system, including a database construction module, a data normalization module, a frequency response curve predictor establishment module, a parameter adjustment module based on Bayesian optimization, and frequency response curve prediction The offline training module of the device and the online prediction module of the frequency response curve predictor, the database construction module is connected with the data normalization module, and the data normalization module is respectively connected with the parameter adjustment module based on Bayesian optimization and the frequency response curve predictor The offline training module is connected with the frequency response curve predictor online prediction module, the frequency response curve predictor establishment module is connected with the parameter adjustment module based on Bayesian optimization, and the frequency response curve...

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 an XGBoost-based power system dynamic frequency response curve prediction method and system, and the method comprises the steps: firstly, obtaining a diversified database based on a simulation result of a massive anticipated fault scene, randomly dividing the diversified database into a training data set and a test data set, and carrying out the normalization processing of the two data sets; secondly, constructing a frequency response curve predictor based on an XGBoost integrated learning model, and determining an optimal hyper-parameter by using a Bayesian optimization model; and finally, carrying out iterative learning on the frequency response curve predictor by utilizing the training data set, and carrying out online evaluation on the dynamic frequency response of the system under a given expected fault or a current operation state by utilizing the trained frequency response curve predictor. According to the XGBoost model disclosed by the invention, the dependency on a sample is reduced; the automatic tuning of hyper-parameters in the XGBoost model is realized through Bayesian optimization, and the prediction of the whole frequency response curve under the disturbance event is realized.

Description

technical field [0001] The invention relates to the technical field of electric power system security, in particular to a method and system for predicting dynamic frequency response curves of electric power systems based on XGBoost. Background technique [0002] With the high proportion of wind power, photovoltaic and other new energy units connected to the grid and the large-scale decommissioning of coal power units, the starting capacity of conventional synchronous power supplies with rotational inertia is constantly being replaced, the inertia level of the power system is greatly reduced, and the frequency adjustment capability is weakened. At the same time, the feed-in of large-capacity UHVDC transmission causes a huge amount of active power impact after a single DC is blocked, further increasing the frequency safety risk of the power system. In recent years, major power outages such as "8.9" in the UK power grid and "9.28" in Australia have caused domestic and foreign r...

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): G06Q10/04G06Q10/06G06Q50/06G06F30/27G06N20/20G06N7/00G06F111/10
CPCG06Q10/04G06Q10/06393G06Q50/06G06F30/27G06N20/20G06F2111/10G06N7/01Y04S10/50
Inventor 司瑞华邵红博王传捷于琳琳王泽张丽华李甜甜刘万勋
Owner ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER
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