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

Extra-high voltage transmission line loss prediction method based on quantum ant colony optimization RBF network

A technology of RBF network and prediction method is applied in the field of UHV transmission line loss prediction based on quantum ant colony optimization of RBF network. Achieve the effect of good rapid evolution and optimization ability, simple calculation process and good precision

Inactive Publication Date: 2020-02-07
CENT CHINA BRANCH OF STATE GRID CORP OF CHINA
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In recent years, deep learning technology has become a hot spot in the direction of artificial intelligence. This technology provides a convenient way to find the nonlinear relationship between parameters; but so far, the line loss calculation method based on deep learning used in China is mostly used in distribution network Among them, there is no line loss prediction method for transmission lines under special working conditions of 1000kV UHV
Under this operating condition, the corona loss is obvious and is easily affected by the surrounding environment, especially under high temperature and rainwater environment, the electric field distortion is serious; secondly, the corona discharge intensity will also increase, resulting in an impact on the ground level electric field

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
  • Extra-high voltage transmission line loss prediction method based on quantum ant colony optimization RBF network
  • Extra-high voltage transmission line loss prediction method based on quantum ant colony optimization RBF network
  • Extra-high voltage transmission line loss prediction method based on quantum ant colony optimization RBF network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Below in conjunction with accompanying drawing and embodiment describe in detail:

[0037] 1. Method

[0038] 1. Steps of this method

[0039] As shown in Figure ①, this method includes the following steps:

[0040] ① Data preprocessing 11;

[0041] ②Establish characteristic index system12;

[0042] ③ Determine the neural network structure 13;

[0043] ④Quantum ant colony algorithm optimizes the connection parameters of the network output layer14;

[0044] ⑤ Use alternate optimization to train the neural network 15;

[0045] ⑥Predict UHV line loss value, analyze and predict model 16.

[0046] 2. Working mechanism

[0047] The working mechanism of the present invention is briefly described below:

[0048]First, preprocess the acquired electrical data and environmental data. For electrical data, abnormal data due to metering faults should be removed through line loss statistics. For environmental data, default values ​​should be removed, and the two types of data ...

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 an extra-high voltage transmission line loss prediction method based on a quantum ant colony optimization RBF network, and belongs to the technical field of combination of an electric power system and deep learning. The method comprises the following steps: (1) preprocessing data; (2),establishing a characteristic index system; 3, determining a neural network structure; (4)optimizing connection parameters of a network output layer by a quantum ant colony algorithm; (5) training the neural network by using an alternate optimization mode; (6) predicting the extra-high voltage line loss value, and analyzing the prediction model. According to the invention, by use of a neural network calculation mode, various nonlinear relationships are easy to fit, calculation detailsdo not need to be manually controlled when the relationship between input parameters and line loss is found, and use is simple; the RBF neural network is used for guaranteeing that the training speedis high, the local approximation characteristic is achieved, and the calculation process is simple; the quantum ant colony algorithm is introduced into the optimization process of the neural network,and the problem that the optimization of the neural network is easy to fall into the local optimal solution is improved.

Description

technical field [0001] The invention belongs to the technical field of power system combined with deep learning, and in particular relates to a method for predicting UHV transmission line loss based on quantum ant colony optimization RBF network. Background technique [0002] With the rapid expansion of the scale of the power system, its network structure tends to be complex, which brings difficulties to the calculation of the theoretical power grid loss; at the same time, the application of the grid metering automation system enhances the monitoring ability of the grid, and the grid company can more conveniently collect the power grid. Various data based on the theoretical calculation of power grid loss. The currently used UHV transmission line loss calculation system mainly obtains the statistical value of the line loss value through the difference between the electricity at both ends of the transmission line, and there are large errors; in order to meet the increasingly 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): G06F30/27G06N3/08G06K9/62G06F113/04G06F113/16
CPCG06N3/086G06N3/084G06F18/23G06F18/213
Inventor 杨建华姜曼牛寅生唐登平明登岳汪应春余明琼肖达强白顺明刘定宜
Owner CENT CHINA BRANCH OF STATE GRID CORP OF CHINA
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