Fast probabilistic power flow calculation method of improved extreme learning machine considering power flow characteristics

A technology of probabilistic power flow calculation and extreme learning machine, which is applied in the field of electric power system and its automation, can solve the problems of rising hidden layer parameter error and limited feature extraction ability of shallow structure, so as to improve fitting ability, reduce fitting difficulty, The effect of improving the fitting effect

Active Publication Date: 2020-01-10
CHONGQING UNIV +2
View PDF15 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the application of ELM to PPF calculation still needs to overcome the limited ability to extract features of the shallow structure, and the random generation of hidden layer parameters causes the error to increase.

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 probabilistic power flow calculation method of improved extreme learning machine considering power flow characteristics
  • Fast probabilistic power flow calculation method of improved extreme learning machine considering power flow characteristics
  • Fast probabilistic power flow calculation method of improved extreme learning machine considering power flow characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] see Figure 1 to Figure 3 , an improved extreme learning machine fast probabilistic power flow calculation method considering power flow characteristics, mainly includes the following steps:

[0042] 1) Obtain the basic data of the power network.

[0043] Furthermore, the basic data of the electric power network mainly includes active power, reactive power, voltage amplitude, voltage phase angle, branch active power and reactive power of electric power network nodes.

[0044] 2) Based on the basic data of the power network, establish a mapping relationship f:P i , Q i → U i , θ i . Among them, P i , Q i Denote the active power and reactive power injected by node i, respectively. u i , θ i Respectively represent the voltage amplitude and voltage phase angle of node i.

[0045] 3) Decompose the mapping relationship and establish an extreme learning machine neural network.

[0046] Further, the main steps of establishing the extreme learning machine neural netw...

Embodiment 2

[0070] The improved extreme learning machine fast probabilistic power flow calculation method considering the characteristics of the power flow mainly includes the following steps:

[0071] 1) Obtain the basic data of the power network.

[0072] 2) Based on the basic data of the power network, establish a mapping relationship f:P i , Q i → U i , θ i . Among them, P i , Q i Denote the active power and reactive power injected by node i, respectively. u i , θ i represent nodes respectively i voltage amplitude and voltage phase angle.

[0073] 3) Decompose the mapping relationship and establish an extreme learning machine neural network.

[0074] 4) Optimize the hidden layer parameters of the extreme learning machine neural network, thereby establishing an improved extreme learning machine neural network.

[0075] 5) Input the basic data of the power network into the neural network of the improved extreme learning machine, and calculate the probability flow of the powe...

Embodiment 3

[0077] The main steps of the improved extreme learning machine fast probability power flow calculation method considering the characteristics of the power flow are shown in Example 2, wherein the main steps of establishing the extreme learning machine neural network are as follows:

[0078] 1) The mapping relationship f:P i , Q i → U i , θ i Decomposed into mapping relationship f 1 :P i , Q i →P ij , Q ij and the mapping relationship f 2 :P ij , Q ij → U i , θ i .

[0079] 2) Based on the mapping relationship f 1 :P i , Q i →P ij , Q ij , to establish the first-stage extreme learning machine neural network. Among them, the input layer is the active power P injected by node i i and the reactive power Q injected by node i i . The hidden layers include unsupervised layers with ELM sparse autoencoder, supervised layers with ELM original algorithm and supervised layers with error correction module. The output layer is the branch active power P of the line ij ...

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 probabilistic power flow calculation method of an improved extreme learning machine considering power flow characteristics. The method mainly comprises the steps of 1) obtaining basic data of a power network; 2) establishing a mapping relationship f: Pi, Qi to Ui, [theta]i based on the basic data of the power network; 3) decomposing the mapping relationship, and establishing an extreme learning machine neural network; 4) optimizing hidden layer parameters of the extreme learning machine neural network so as to establish an improved extreme learning machine neuralnetwork; 5) inputting the basic data of the power network into the improved extreme learning machine neural network, and calculating to obtain the probabilistic power flow of the power network. According to the invention, a time-consuming solving process for a large-scale high-dimensional complex nonlinear power flow equation in PPF calculation of a high-precision simulation method is replaced, so that engineering actual requirements of PPF calculation on precision and speed are considered.

Description

technical field [0001] The invention relates to the field of electric power system and automation thereof, in particular to an improved extreme learning machine fast probability power flow calculation method considering power flow characteristics. Background technique [0002] The increasing uncertainty of sources and loads makes Probabilistic Power Flow (PPF) an important tool for power system planning, operation and reliability assessment analysis. PPF calculation is mainly divided into simulation method, analytical method and approximate method. The simulation method solves a large number of high-dimensional and complex nonlinear power flow samples to ensure the accuracy of statistical analysis of state quantities, but the calculation speed is insufficient. The analytical method calculates the probability distribution of the state quantity by calculating the relationship convolution between the input random variables, and the approximate method uses the digital character...

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): H02J3/06G06N3/02
CPCG06N3/02H02J3/06
Inventor 余娟高倩杨知方代伟雷星雨余红欣王洪彬
Owner CHONGQING 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