SIA OpenIR  > 工业控制网络与系统研究室
Power System Anomaly Detection Based on OCSVM Optimized by Improved Particle Swarm Optimization
Wang ZF(王忠锋)1,2,3; Fu YT(付亚同)1,2,3,4; Song CH(宋纯贺)1,2,3; Zeng P(曾鹏)1,2,3; Qiao L(乔林)5
Department工业控制网络与系统研究室
Source PublicationIEEE ACCESS
ISSN2169-3536
2019
Volume7Pages:181580-181588
Indexed BySCI ; EI
EI Accession number20200408066360
WOS IDWOS:000509486900012
Contribution Rank1
Funding OrganizationState Grid Corporation Science and Technology Project [SGLNXT00YJJS1800110]
KeywordPower system anomaly detection one-class support vector machine particle swarm optimization adaptive speed weighting adaptive population splitting
Abstract

This paper tries to solve anomaly detection, a very important issue in ensuring the safe and stable operation of power system. As the proportion of abnormal data in the operation of power system is very small, a one-class support vector machine (OCSVM) is adopted in this paper, which is suitable for classification of unbalanced data. However, the performance of OCSVM is sensitive to its parameters, and an unsuitable choice will decrease the classification accuracy and generalization ability of it. In this paper, particle swarm optimization (PSO) is used to optimize the parameters of OCSVM. The original PSO algorithm converges slowly and easily falls into local optimum. To overcome this issue, this paper proposes an improved PSO algorithm for parameters optimization, in which adaptive speed weighting and adaptive population splitting are introduced to improve the convergence speed of the algorithm and help the algorithm jump out of the local optimal position. Experiments on standard benchmarks and real power system experimental data sets demonstrate the effectiveness of the proposed algorithm.

Language英语
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS KeywordSUPPORT
WOS Research AreaComputer Science ; Engineering ; Telecommunications
Funding ProjectState Grid Corporation Science and Technology Project[SGLNXT00YJJS1800110]
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/26221
Collection工业控制网络与系统研究室
Corresponding AuthorSong CH(宋纯贺)
Affiliation1.Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang, China
2.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
4.University of Chinese Academy of Sciences, Beijing 100049, China
5.State Grid Liaoning Electric Power Company Ltd., Shenyang, China
Recommended Citation
GB/T 7714
Wang ZF,Fu YT,Song CH,et al. Power System Anomaly Detection Based on OCSVM Optimized by Improved Particle Swarm Optimization[J]. IEEE ACCESS,2019,7:181580-181588.
APA Wang ZF,Fu YT,Song CH,Zeng P,&Qiao L.(2019).Power System Anomaly Detection Based on OCSVM Optimized by Improved Particle Swarm Optimization.IEEE ACCESS,7,181580-181588.
MLA Wang ZF,et al."Power System Anomaly Detection Based on OCSVM Optimized by Improved Particle Swarm Optimization".IEEE ACCESS 7(2019):181580-181588.
Files in This Item:
File Name/Size DocType Version Access License
Power System Anomaly(4082KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang ZF(王忠锋)]'s Articles
[Fu YT(付亚同)]'s Articles
[Song CH(宋纯贺)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang ZF(王忠锋)]'s Articles
[Fu YT(付亚同)]'s Articles
[Song CH(宋纯贺)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang ZF(王忠锋)]'s Articles
[Fu YT(付亚同)]'s Articles
[Song CH(宋纯贺)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Power System Anomaly Detection Based on OCSVM Optimized by Improved Particle Swarm Optimization.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.