Generalized load graphical forecasting method based on modal decomposition

IF 1.9 Q4 ENERGY & FUELS Global Energy Interconnection Pub Date : 2024-04-01 DOI:10.1016/j.gloei.2024.04.005
Lizhen Wu , Peixin Chang , Wei Chen , Tingting Pei
{"title":"Generalized load graphical forecasting method based on modal decomposition","authors":"Lizhen Wu ,&nbsp;Peixin Chang ,&nbsp;Wei Chen ,&nbsp;Tingting Pei","doi":"10.1016/j.gloei.2024.04.005","DOIUrl":null,"url":null,"abstract":"<div><p>In a “low-carbon” context, the power load is affected by the coupling of multiple factors, which gradually evolves from the traditional “pure load” to the generalized load with the dual characteristics of “load + power supply.” Traditional time-series forecasting methods are no longer suitable owing to the complexity and uncertainty associated with generalized loads. From the perspective of image processing, this study proposes a graphical short-term prediction method for generalized loads based on modal decomposition. First, the datasets are normalized and feature-filtered by comparing the results of Xtreme gradient boosting, gradient boosted decision tree, and random forest algorithms. Subsequently, the generalized load data are decomposed into three sets of modalities by modal decomposition, and red, green, and blue (RGB) images are generated using them as the pixel values of the R, G, and B channels. The generated images are diversified, and an optimized DenseNet neural network was used for training and prediction. Finally, the base load, wind power, and photovoltaic power generation data are selected, and the characteristic curves of the generalized load scenarios under different permeabilities of wind power and photovoltaic power generation are obtained using the density-based spatial clustering of applications with noise algorithm. Based on the proposed graphical forecasting method, the feasibility of the generalized load graphical forecasting method is verified by comparing it with the traditional time-series forecasting method.</p></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2096511724000264/pdf?md5=c88651272de38919b8ce0c9052b6fb8b&pid=1-s2.0-S2096511724000264-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Global Energy Interconnection","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2096511724000264","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

Abstract

In a “low-carbon” context, the power load is affected by the coupling of multiple factors, which gradually evolves from the traditional “pure load” to the generalized load with the dual characteristics of “load + power supply.” Traditional time-series forecasting methods are no longer suitable owing to the complexity and uncertainty associated with generalized loads. From the perspective of image processing, this study proposes a graphical short-term prediction method for generalized loads based on modal decomposition. First, the datasets are normalized and feature-filtered by comparing the results of Xtreme gradient boosting, gradient boosted decision tree, and random forest algorithms. Subsequently, the generalized load data are decomposed into three sets of modalities by modal decomposition, and red, green, and blue (RGB) images are generated using them as the pixel values of the R, G, and B channels. The generated images are diversified, and an optimized DenseNet neural network was used for training and prediction. Finally, the base load, wind power, and photovoltaic power generation data are selected, and the characteristic curves of the generalized load scenarios under different permeabilities of wind power and photovoltaic power generation are obtained using the density-based spatial clustering of applications with noise algorithm. Based on the proposed graphical forecasting method, the feasibility of the generalized load graphical forecasting method is verified by comparing it with the traditional time-series forecasting method.

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
基于模态分解的通用负荷图形预测方法
在 "低碳 "背景下,电力负荷受到多种因素的耦合影响,从传统的 "纯负荷 "逐渐演变为具有 "负荷+电源 "双重特性的广义负荷。由于广义负荷的复杂性和不确定性,传统的时间序列预测方法已不再适用。本研究从图像处理的角度出发,提出了一种基于模态分解的广义负荷图形化短期预测方法。首先,通过比较 Xtreme 梯度提升算法、梯度提升决策树算法和随机森林算法的结果,对数据集进行归一化和特征过滤。然后,通过模态分解将广义负载数据分解为三组模态,并使用它们作为 R、G 和 B 通道的像素值生成红、绿、蓝(RGB)图像。生成的图像是多样化的,并使用优化的 DenseNet 神经网络进行训练和预测。最后,选取基本负荷、风力发电和光伏发电数据,利用基于密度的带噪声应用空间聚类算法,得到风力发电和光伏发电不同渗透率下的广义负荷场景特征曲线。基于所提出的图形预测方法,通过与传统的时间序列预测方法进行比较,验证了广义负荷图形预测方法的可行性。
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 去求助
来源期刊
Global Energy Interconnection
Global Energy Interconnection Engineering-Automotive Engineering
CiteScore
5.70
自引率
0.00%
发文量
985
审稿时长
15 weeks
期刊最新文献
Vibration and noise mechanism of a 110 kV transformer under DC bias based on finite element method A novel cascaded H-bridge photovoltaic inverter with flexible arc suppression function Consideration of the influence of supports in modeling the electromagnetic fields of 25 kV traction networks under emergency conditions Impact of the carbon market on investment benefits of power-grid enterprises in China: A system dynamics analysis Optimized scheduling of integrated energy systems for low carbon economy considering carbon transaction costs
×
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