Unlock instant, AI-driven research and patent intelligence for your innovation.

Power distribution network fault outage rate prediction method and system based on improved random forest

A distribution network fault, random forest technology, applied in forecasting, computer components, computing models, etc., can solve the problems of low accuracy, large limitations, and slow convergence speed of multi-classification problems, and achieve the level of failure and blackout rate. , Optimized parameter selection, the effect of fast training speed

Pending Publication Date: 2020-04-17
STATE GRID SHANDONG ELECTRIC POWER +1
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, the research on the prediction of power outage rate of distribution network faults mainly includes analytical method and simulation method, but they all rely on the grid structure to build mathematical models, which are highly limited; at the same time, from the perspective of data-driven, machine learning algorithms are used to conduct power outages. However, artificial neural networks have shortcomings such as difficult parameter optimization and slow convergence speed. Although support vector machines overcome the problems of slow convergence speed and over-fitting of artificial neural networks, they also have problems in processing large Insufficient ability of sample data and low accuracy in solving multi-classification problems

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 distribution network fault outage rate prediction method and system based on improved random forest
  • Power distribution network fault outage rate prediction method and system based on improved random forest
  • Power distribution network fault outage rate prediction method and system based on improved random forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] See attached figure 1 As shown, this embodiment discloses a method for predicting the level of power outage rate of distribution network faults based on improved random forest, the method includes the following steps:

[0031] Step 1, processing the distribution network fault history record into available data types, including the value of each feature quantity in Table 1 as a feature quantity;

[0032] Step 2. According to the failure rate of various facilities in the distribution network, according to the interval distribution, the failure rate level is classified and numbered as the label of the sample set. The random forest algorithm is a supervised learning algorithm, and the feature quantity needs to be given first s Mark;

[0033] Step 3, using the principal component analysis method to perform weight analysis on the input data, and obtain the processed input data according to the weight coefficient;

[0034] Step 4: Use the improved random forest algorithm to ...

Embodiment 2

[0063] The purpose of this embodiment is to provide a computing device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, the following steps are implemented, including:

[0064] Step 1. Process the fault history records of the distribution network into available data types as feature quantities;

[0065] Step 2. According to the failure rate of various facilities in the distribution network, according to the interval distribution, the failure rate level is classified and numbered as the label of the sample set;

[0066] Step 3, using the principal component analysis method to perform weight analysis on the input data, and obtain the processed input data according to the weight coefficient;

[0067] Step 4: Use the improved random forest algorithm to train the data to obtain a prediction model.

Embodiment 3

[0069] The purpose of this embodiment is to provide a computer-readable storage medium.

[0070] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are performed:

[0071] Step 1. Process the fault history records of the distribution network into available data types as feature quantities;

[0072] Step 2. According to the failure rate of various facilities in the distribution network, according to the interval distribution, the failure rate level is classified and numbered as the label of the sample set;

[0073] Step 3, using the principal component analysis method to perform weight analysis on the input data, and obtain the processed input data according to the weight coefficient;

[0074] Step 4: Use the improved random forest algorithm to train the data to obtain a prediction model.

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 power distribution network fault outage rate prediction method and system based on an improved random forest, and the method comprises the steps: obtaining power distributionnetwork fault outage related data, extracting a characteristic quantity, and calculating a fault outage reliability parameter based on the proposed characteristic quantity; according to the fault power failure reliability parameters and interval distribution, classifying and numbering fault rate levels to serve as labels of a sample set; carrying out weight analysis on different characteristic quantities by utilizing a principal component analysis method and obtaining a weight coefficient; and obtaining a prediction model by using a random forest algorithm optimized by a grey wolf optimization algorithm according to the characteristic quantity data set and the sample set label data after principal component analysis processing. Compared with the prior art, the method is not limited to a grid structure of the power distribution network any more, and the fault outage rate level of the power distribution network is effectively predicted from fault record data.

Description

technical field [0001] The invention belongs to the technical field of power outage reliability evaluation for distribution network faults, and in particular relates to a method and system for predicting power outage rate of distribution network faults based on improved random forests. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] The distribution network in the power system is responsible for the transmission and distribution of electric energy, which has an important impact on the stability of the power system. According to statistics, 80% of power outages are caused by power failures in the distribution network. [0004] The power outage of distribution network faults is related to many factors, so the prediction of power outage rate needs to consider the influence of line structure, weather conditions, human factors and other aspect...

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): G06K9/62G06N3/00G06Q10/04G06Q50/06
CPCG06N3/006G06Q10/04G06Q50/06G06F18/2135G06F18/24323
Inventor 王志涛王振华胡彦乐周家闻李清泉孙敬业孟硕杨栋刘均鹏来倩尹延凯边金龙张敏
Owner STATE GRID SHANDONG ELECTRIC POWER