A Transformer District Line Loss Calculation Method Based on Data Mining and Machine Learning

Xiaowei Miao, Zhujian Ou, Ming Yang, Jian-ping Yuan, Yue Cao, Shiying Huang, Wangchun Liu
{"title":"A Transformer District Line Loss Calculation Method Based on Data Mining and Machine Learning","authors":"Xiaowei Miao, Zhujian Ou, Ming Yang, Jian-ping Yuan, Yue Cao, Shiying Huang, Wangchun Liu","doi":"10.1109/AEEES54426.2022.9759810","DOIUrl":null,"url":null,"abstract":"Transformer district (TD) line loss is an important economic and technical index for the economic operation of power system. The traditional TD line loss management adopts the uniform fixed interval as a reasonable interval, which is not conducive to lean management. This paper presents an accurate quantization method of TD line loss based on data mining and machine learning. Firstly, the proposed method forms the electrical characteristic index system of TD. On this basis, the proposed method combined the improved K-means method with clustering effect comprehensive evaluation index to obtain the optimal classification results of massive TDs. Then, according to the objective weight extraction method, the key impact factor set of the TD line loss are obtained, so as to obtain the feature images of each TD. Finally, the accurate quantification of TD line loss is realized by the proposed TD line loss calculation model based on the BP neural network and kernel density estimation. The effectiveness of the proposed method are verified by simulations based on the real TD data.","PeriodicalId":252797,"journal":{"name":"2022 4th Asia Energy and Electrical Engineering Symposium (AEEES)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 4th Asia Energy and Electrical Engineering Symposium (AEEES)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AEEES54426.2022.9759810","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Transformer district (TD) line loss is an important economic and technical index for the economic operation of power system. The traditional TD line loss management adopts the uniform fixed interval as a reasonable interval, which is not conducive to lean management. This paper presents an accurate quantization method of TD line loss based on data mining and machine learning. Firstly, the proposed method forms the electrical characteristic index system of TD. On this basis, the proposed method combined the improved K-means method with clustering effect comprehensive evaluation index to obtain the optimal classification results of massive TDs. Then, according to the objective weight extraction method, the key impact factor set of the TD line loss are obtained, so as to obtain the feature images of each TD. Finally, the accurate quantification of TD line loss is realized by the proposed TD line loss calculation model based on the BP neural network and kernel density estimation. The effectiveness of the proposed method are verified by simulations based on the real TD data.
基于数据挖掘和机器学习的变压器区线损计算方法
变压器区线损是电力系统经济运行的一项重要经济技术指标。传统输配电线损管理采用统一的固定间隔作为合理间隔,不利于精益管理。提出了一种基于数据挖掘和机器学习的输配电线损精确量化方法。首先,该方法形成了输配电系统的电气特性指标体系。在此基础上,将改进的K-means方法与聚类效果综合评价指标相结合,得到海量td的最优分类结果。然后,根据客观权重提取方法,得到TD线损的关键影响因子集,从而得到每个TD的特征图像。最后,提出了基于BP神经网络和核密度估计的输配电线损计算模型,实现了输配电线损的准确量化。基于实际输配电数据的仿真验证了该方法的有效性。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信