HOME
About Journal
Historical evolution
Journal Honors
Editorial Board
Members of Committee
Director of the Committee
President and Editor in chief
Submission Guide
Instructions for Authors
Manuscript Processing Flow
Model Text
Procedures for Submission
Academic Influence
Open Access
Ethics&Policies
Publication Ethics Statement
Peer Review Process
Academic Misconduct Identification and Treatment
Advertising and Marketing
Correction and Retraction
Conflict of Interest
Authorship & Copyright
Contact Us
Chinese
Site search
Article Number
On-site news
English title
Author's English Name
Author's Chinese Name
Chinese name of the company
English name of the compan
Chinese keywords
English keywords
Chinese Abstract
English Abstract
Fund projects
Article Number
Chinese Title
English title
Author's English Name
Author's Chinese Name
Chinese name of the company
English name of the compan
Chinese keywords
English keywords
Chinese Abstract
English Abstract
Fund projects
文章摘要
基于迁移学习的智能静态电压稳定评估方案
Intelligent static voltage stability assessment schemebased on transfer learning
Received:September 05, 2021
Revised:September 23, 2021
DOI：
10.19753/j.issn1001-1390.2022.02.013
中文关键词
:
静态电压稳定评估
最大相关最小冗余准则
梯度提升分段线性回归树
迁移学习
英文关键词
:
static voltage stability assessment, maximal relevance minimal redundancy criterion, gradient boosting with piecewise linear regression trees, transfer learning
基金项目
:
国家自然科学基金资助项目：计及热量迁移动态过程的电热耦合系统时空异构动态优化调度方法研究（ 52007103）;信息物理融合防御与控制系统宜昌市重点实验室（三峡大学)基金项目（2020XXRH02）
Author Name
Affiliation
E-mail
Yan Guanghui
College of Electrical Engineering and New Energy
,
China Three Gorges University
1667906187@qq.com
Liu Songkai
College of Electrical Engineering and New Energy
,
China Three Gorges University
Liusongk@163.com
Zhang Lei
College of Electrical Engineering and New Energy
,
China Three Gorges University
258750851@qq.com
Gong Xiaoyu
*
College of Economics and Management
,
China Three Gorges University
1972258441@qq.com
Hits
:
1496
Download times
:
373
中文摘要
:
由于电力系统拓扑结构复杂多变,基于数据驱动的静态电压稳定评估通常存在模型泛化能力不足的问题。针对该问题,文中提出了一种基于迁移学习的智能静态电压稳定评估方案。首先,基于最大相关最小冗余( Maximal Relevance Minimal Redundancy,MRMR)准则和shapley值构建S-MRMR特征选择框架,对离线生成的数据集进行数据降维；然后,基于梯度提升分段线性回归树(Gradient Boosting With Piecewise Linear Regression Trees,GBDT-PL)算法构建静态电压稳定评估模型,提取电力系统运行特征与静态电压稳定指标间的映射关系；最后,利用迁移学习对GBDT-PL模型进行实时更新,提高模型的泛化能力。在由电力系统仿真软件PSS/E提供的23节点系统和1648节点系统上的仿真结果表明,文中所提方案对电力系统拓扑结构变化具有较强的鲁棒性,能够满足在线电压稳定评估的要求,为数据驱动方法实际应用于静态电压稳定评估提供了有益的参考。
英文摘要
:
View Full Text
View/Add Comment
Download reader
Close
Home
About Journal
Historical evolution
Journal Honors
Editorial Board
Members of Committee
Director of the Committee
President and Editor in chief
Submission Guide
Instructions for Authors
Manuscript Processing Flow
Model Text
Procedures for Submission
Academic Influence
Open Access
Ethics&Policies
Publication Ethics Statement
Peer Review Process
Academic Misconduct Identification and Treatment
Advertising and Marketing
Correction and Retraction
Conflict of Interest
Authorship & Copyright
Contact Us
中文页面