Constraint Learning-based Optimal Power Dispatch for Active Distribution Networks with Extremely Imbalanced Data

IF 6.9 2区 工程技术 Q2 ENERGY & FUELS CSEE Journal of Power and Energy Systems Pub Date : 2023-12-28 DOI:10.17775/CSEEJPES.2023.05970
Yonghua Song;Ge Chen;Hongcai Zhang
{"title":"Constraint Learning-based Optimal Power Dispatch for Active Distribution Networks with Extremely Imbalanced Data","authors":"Yonghua Song;Ge Chen;Hongcai Zhang","doi":"10.17775/CSEEJPES.2023.05970","DOIUrl":null,"url":null,"abstract":"Transition towards carbon-neutral power systems has necessitated optimization of power dispatch in active distribution networks (ADNs) to facilitate integration of distributed renewable generation. Due to unavailability of network topology and line impedance in many distribution networks, physical model-based methods may not be applicable to their operations. To tackle this challenge, some studies have proposed constraint learning, which replicates physical models by training a neural network to evaluate feasibility of a decision (i.e., whether a decision satisfies all critical constraints or not). To ensure accuracy of this trained neural network, training set should contain sufficient feasible and infeasible samples. However, since ADNs are mostly operated in a normal status, only very few historical samples are infeasible. Thus, the historical dataset is highly imbalanced, which poses a significant obstacle to neural network training. To address this issue, we propose an enhanced constraint learning method. First, it leverages constraint learning to train a neural network as surrogate of ADN's model. Then, it introduces Synthetic Minority Oversampling Technique to generate infeasible samples to mitigate imbalance of historical dataset. By incorporating historical and synthetic samples into the training set, we can significantly improve accuracy of neural network. Furthermore, we establish a trust region to constrain and thereafter enhance reliability of the solution. Simulations confirm the benefits of the proposed method in achieving desirable optimality and feasibility while maintaining low computational complexity.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":"10 1","pages":"51-65"},"PeriodicalIF":6.9000,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375977","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CSEE Journal of Power and Energy Systems","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10375977/","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

Transition towards carbon-neutral power systems has necessitated optimization of power dispatch in active distribution networks (ADNs) to facilitate integration of distributed renewable generation. Due to unavailability of network topology and line impedance in many distribution networks, physical model-based methods may not be applicable to their operations. To tackle this challenge, some studies have proposed constraint learning, which replicates physical models by training a neural network to evaluate feasibility of a decision (i.e., whether a decision satisfies all critical constraints or not). To ensure accuracy of this trained neural network, training set should contain sufficient feasible and infeasible samples. However, since ADNs are mostly operated in a normal status, only very few historical samples are infeasible. Thus, the historical dataset is highly imbalanced, which poses a significant obstacle to neural network training. To address this issue, we propose an enhanced constraint learning method. First, it leverages constraint learning to train a neural network as surrogate of ADN's model. Then, it introduces Synthetic Minority Oversampling Technique to generate infeasible samples to mitigate imbalance of historical dataset. By incorporating historical and synthetic samples into the training set, we can significantly improve accuracy of neural network. Furthermore, we establish a trust region to constrain and thereafter enhance reliability of the solution. Simulations confirm the benefits of the proposed method in achieving desirable optimality and feasibility while maintaining low computational complexity.
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
基于约束学习的极不平衡数据有源配电网优化电力调度
向碳中性电力系统过渡需要优化有源配电网(ADN)中的电力调度,以促进分布式可再生能源发电的整合。由于许多配电网不具备网络拓扑结构和线路阻抗,基于物理模型的方法可能不适用于其运行。为应对这一挑战,一些研究提出了约束学习方法,即通过训练神经网络来评估决策的可行性(即决策是否满足所有关键约束条件),从而复制物理模型。为确保训练神经网络的准确性,训练集应包含足够多的可行和不可行样本。然而,由于 ADN 大多在正常状态下运行,只有极少数历史样本是不可行的。因此,历史数据集是高度不平衡的,这给神经网络训练带来了很大的障碍。针对这一问题,我们提出了一种增强型约束学习方法。首先,它利用约束学习来训练一个神经网络,作为 ADN 模型的替代。然后,引入合成少数群体过度采样技术来生成不可行样本,以减轻历史数据集的不平衡。通过将历史样本和合成样本纳入训练集,我们可以显著提高神经网络的准确性。此外,我们还建立了一个信任区域来约束并提高解决方案的可靠性。仿真证实了所提方法在实现理想的最优性和可行性方面的优势,同时保持了较低的计算复杂度。
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
CiteScore
11.80
自引率
12.70%
发文量
389
审稿时长
26 weeks
期刊介绍: The CSEE Journal of Power and Energy Systems (JPES) is an international bimonthly journal published by the Chinese Society for Electrical Engineering (CSEE) in collaboration with CEPRI (China Electric Power Research Institute) and IEEE (The Institute of Electrical and Electronics Engineers) Inc. Indexed by SCI, Scopus, INSPEC, CSAD (Chinese Science Abstracts Database), DOAJ, and ProQuest, it serves as a platform for reporting cutting-edge theories, methods, technologies, and applications shaping the development of power systems in energy transition. The journal offers authors an international platform to enhance the reach and impact of their contributions.
期刊最新文献
Transient Voltage Support Strategy of Grid-Forming Medium Voltage Photovoltaic Converter in the LCC-HVDC System Front Cover Contents PFL-DSSE: A Personalized Federated Learning Approach for Distribution System State Estimation Front Cover
×
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