Support vector machine based fast Monte Carlo reliability evaluation method for composite power system

A fast Monte Carlo reliability evaluation method for composite power system based on support vector machine (SVM) was proposesd.Firstly,sample data for training the SVM model was obtained by enumerating component failures and calculating the corresponding minimum load shedding.Then,the SVM algorithm...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuxiao LEI, Gengfeng LI, Yuxiong HUANG, Zhaohong BIE
Format: Article
Language:zho
Published: Beijing Xintong Media Co., Ltd 2019-06-01
Series:Dianxin kexue
Subjects:
Online Access:http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2019155/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A fast Monte Carlo reliability evaluation method for composite power system based on support vector machine (SVM) was proposesd.Firstly,sample data for training the SVM model was obtained by enumerating component failures and calculating the corresponding minimum load shedding.Then,the SVM algorithm was used to mine the nonlinear mapping relationship between component failures and minimum load shedding,and the minimum load shedding estimation model was trained.Finally,the model was combined with the Monte Carlo simulation.By randomly sampling component states,for each state,the estimation model obtained by the training directly gave the minimum load shedding,thereby achieving a rapid assessment of the reliability of the composite power system.The proposed method is applied to the IEEE RTS 79 system,which verifies its effectiveness.
ISSN:1000-0801