Real-time small-signal security assessment using graph neural networks

IF 4.8 2区 工程技术 Q2 ENERGY & FUELS Sustainable Energy Grids & Networks Pub Date : 2024-07-02 DOI:10.1016/j.segan.2024.101469
Glory Justin, Santiago Paternain
{"title":"Real-time small-signal security assessment using graph neural networks","authors":"Glory Justin,&nbsp;Santiago Paternain","doi":"10.1016/j.segan.2024.101469","DOIUrl":null,"url":null,"abstract":"<div><p>Security assessment is one of the most crucial functions of a power system operator. However, growing complexity and unpredictability make this an increasingly complex and computationally difficult task. In recent times, machine learning methods have gained attention for their ability to handle complex modeling applications. Convolutional neural networks (CNNs) in particular, are widely used in literature for their adaptability for classification problems. While CNNs generate promising results and some real-time advantages, they still require long training times and computational resources. This paper proposes a graph neural network (GNN) approach to the small-signal security assessment problem using data from Phasor Measurement Units (PMUs). Using a GNN, the process for small signal security assessment can be optimized, reducing the time needed from minutes, to less than a second, thus allowing for faster real-time application. Also, using graph properties, optimal PMU placement is determined and the proposed method is shown to perform efficiently under partial observability with limited PMU data. Case studies with simulated data from the IEEE 68-bus system and the NPCC 140-bus system are used to verify the effectiveness of the proposed method showing comparisons with the CNN.</p></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":null,"pages":null},"PeriodicalIF":4.8000,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sustainable Energy Grids & Networks","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S235246772400198X","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

Abstract

Security assessment is one of the most crucial functions of a power system operator. However, growing complexity and unpredictability make this an increasingly complex and computationally difficult task. In recent times, machine learning methods have gained attention for their ability to handle complex modeling applications. Convolutional neural networks (CNNs) in particular, are widely used in literature for their adaptability for classification problems. While CNNs generate promising results and some real-time advantages, they still require long training times and computational resources. This paper proposes a graph neural network (GNN) approach to the small-signal security assessment problem using data from Phasor Measurement Units (PMUs). Using a GNN, the process for small signal security assessment can be optimized, reducing the time needed from minutes, to less than a second, thus allowing for faster real-time application. Also, using graph properties, optimal PMU placement is determined and the proposed method is shown to perform efficiently under partial observability with limited PMU data. Case studies with simulated data from the IEEE 68-bus system and the NPCC 140-bus system are used to verify the effectiveness of the proposed method showing comparisons with the CNN.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用图神经网络进行实时小信号安全评估
安全评估是电力系统运营商最重要的职能之一。然而,日益增长的复杂性和不可预测性使这项任务变得越来越复杂,计算难度也越来越大。近来,机器学习方法因其处理复杂建模应用的能力而备受关注。特别是卷积神经网络(CNN),因其对分类问题的适应性而在文献中得到广泛应用。虽然卷积神经网络能产生可喜的结果并具有一些实时优势,但它们仍然需要较长的训练时间和计算资源。本文提出了一种图神经网络(GNN)方法,利用相量测量单元(PMU)的数据来解决小信号安全评估问题。利用图神经网络,可以优化小信号安全评估过程,将所需时间从几分钟缩短到一秒以内,从而实现更快的实时应用。此外,利用图的特性,还能确定 PMU 的最佳位置,并证明所提出的方法能在 PMU 数据有限的情况下,在部分可观测性条件下高效执行。利用 IEEE 68 总线系统和 NPCC 140 总线系统的模拟数据进行的案例研究验证了所提方法的有效性,并与 CNN 进行了比较。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Sustainable Energy Grids & Networks
Sustainable Energy Grids & Networks Energy-Energy Engineering and Power Technology
CiteScore
7.90
自引率
13.00%
发文量
206
审稿时长
49 days
期刊介绍: Sustainable Energy, Grids and Networks (SEGAN)is an international peer-reviewed publication for theoretical and applied research dealing with energy, information grids and power networks, including smart grids from super to micro grid scales. SEGAN welcomes papers describing fundamental advances in mathematical, statistical or computational methods with application to power and energy systems, as well as papers on applications, computation and modeling in the areas of electrical and energy systems with coupled information and communication technologies.
期刊最新文献
Secured energy data transaction for prosumers under diverse cyberattack scenarios Investigating the long-term benefits of EU electricity highways: The case of the Green Aegean Interconnector Blockchain-enabled transformation: Decentralized planning and secure peer-to-peer trading in local energy networks Integrated real-time dispatch of power and gas systems Two-stage low-carbon economic dispatch of an integrated energy system considering flexible decoupling of electricity and heat on sides of source and load
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1