基于余弦相似度和图卷积网络的电力负荷预测方法

针对现有电力负荷预测模型难以深入提取时空关联特征,模型泛化能力弱,无法同时胜任短期和长期的电力负荷预测的问题,提出一种面向多用户的基于余弦相似度和全局-局部协同图卷积网络的电力负荷预测方法.首先,利用余弦相似度来学习不同节点负荷数据之间的相似模式,以提取深层次的时空关联特征.其次,对影响电力负荷变化趋势的静态全局因素和动态局部因素进行协同建模,以提升模型的泛化能力.最后,通过在一个实测数据集上进行的大量实验,验证了该方法在短期和长期负荷序列预测任务中同时具备有效性和稳定性....

Full description

Saved in:
Bibliographic Details
Published in浙江电力 Vol. 44; no. 1; pp. 68 - 75
Main Authors JI Shan, 姜巍, 景鑫
Format Journal Article
LanguageChinese
Published 杭州迈拓大数据服务有限公司,杭州 310007%国网浙江省电力有限公司科技创新中心,杭州 310007 25.01.2025
Subjects
graph convo-lutional
时空关联特征
multi-node power load forecasting
余弦相似度
多节点电力负荷预测
图卷积
spatiotemporal correlation features
cosine similarity
Online AccessGet full text
ISSN1007-1881
DOI10.19585/j.zjdl.202501007

Cover

Abstract 针对现有电力负荷预测模型难以深入提取时空关联特征,模型泛化能力弱,无法同时胜任短期和长期的电力负荷预测的问题,提出一种面向多用户的基于余弦相似度和全局-局部协同图卷积网络的电力负荷预测方法.首先,利用余弦相似度来学习不同节点负荷数据之间的相似模式,以提取深层次的时空关联特征.其次,对影响电力负荷变化趋势的静态全局因素和动态局部因素进行协同建模,以提升模型的泛化能力.最后,通过在一个实测数据集上进行的大量实验,验证了该方法在短期和长期负荷序列预测任务中同时具备有效性和稳定性.
AbstractList 针对现有电力负荷预测模型难以深入提取时空关联特征,模型泛化能力弱,无法同时胜任短期和长期的电力负荷预测的问题,提出一种面向多用户的基于余弦相似度和全局-局部协同图卷积网络的电力负荷预测方法.首先,利用余弦相似度来学习不同节点负荷数据之间的相似模式,以提取深层次的时空关联特征.其次,对影响电力负荷变化趋势的静态全局因素和动态局部因素进行协同建模,以提升模型的泛化能力.最后,通过在一个实测数据集上进行的大量实验,验证了该方法在短期和长期负荷序列预测任务中同时具备有效性和稳定性.
Abstract_FL To address the challenges of existing power load forecasting models,which struggle to deeply extract spa-tiotemporal correlation features and exhibit weak generalization capabilities—failing to simultaneously manage both short-term and long-term forecasting—this study proposes a multi-user power load forecasting method using cosine similarity and a global-local collaborative graph convolutional network.First,cosine similarity is utilized to learn similar patterns between load data from different nodes,allowing for the deep extraction of spatiotemporal correla-tion features.Second,a collaborative modeling approach is applied to static global factors and dynamic local factors that influence power load trends,enhancing the model's generalization ability.Finally,extensive experiments on a real-world dataset demonstrate the method's effectiveness and robustness in forecasting both short-term and long-term load series.
Author 景鑫
JI Shan
姜巍
AuthorAffiliation 杭州迈拓大数据服务有限公司,杭州 310007%国网浙江省电力有限公司科技创新中心,杭州 310007
AuthorAffiliation_xml – name: 杭州迈拓大数据服务有限公司,杭州 310007%国网浙江省电力有限公司科技创新中心,杭州 310007
Author_FL JING Xin
JI Shan
JIANG Wei
Author_FL_xml – sequence: 1
  fullname: JI Shan
– sequence: 2
  fullname: JIANG Wei
– sequence: 3
  fullname: JING Xin
Author_xml – sequence: 1
  fullname: JI Shan
– sequence: 2
  fullname: 姜巍
– sequence: 3
  fullname: 景鑫
BookMark eNrjYmDJy89LZWCQNDTQM7Q0tTDVz9KrykrJ0TMyMDI1MDQwMGdh4ARRuoYWFoYcDLzFxZlJBgaGhkaWZqaWnAxOT-fverKr78nemU_3LHs-e8eTPXue7lr2dFLP09n7nvZuf758_fO9E5_vnvN8VsvzKVufds1-sWX-i97tLxe1PNva_Wzazmebp_IwsKYl5hSn8kJpboZQN9cQZw9dH393T2dHH91isP1JqUbJRikGaZamyYkWqcYWqQapxgaJycZJQHclmZoamZmbJZqmJlkkW5hZmiUZWJonJyWap6QZpSQZJyeZWZobczOoQswtT8xLS8xLj8_KLy3KA9oYD_Iw3L_GAHEaZm8
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.19585/j.zjdl.202501007
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL A power load forecasting method using cosine similarity and a graph convolutional network
EndPage 75
ExternalDocumentID zjdl202501007
GrantInformation_xml – fundername: 国网浙江省电力有限公司科技项目
  funderid: (B311JZ230003)
GroupedDBID -03
2B.
4A8
92I
93N
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CEKLB
GROUPED_DOAJ
PSX
TCJ
ID FETCH-LOGICAL-s1007-be2c2d0f95ca8e38e0e30ac3b881b552676a5eb8c8696b097cba7df2db3cb6973
ISSN 1007-1881
IngestDate Thu May 29 03:55:40 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords graph convo-lutional
时空关联特征
multi-node power load forecasting
余弦相似度
多节点电力负荷预测
图卷积
spatiotemporal correlation features
cosine similarity
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1007-be2c2d0f95ca8e38e0e30ac3b881b552676a5eb8c8696b097cba7df2db3cb6973
PageCount 8
ParticipantIDs wanfang_journals_zjdl202501007
PublicationCentury 2000
PublicationDate 2025-01-25
PublicationDateYYYYMMDD 2025-01-25
PublicationDate_xml – month: 01
  year: 2025
  text: 2025-01-25
  day: 25
PublicationDecade 2020
PublicationTitle 浙江电力
PublicationTitle_FL Zhejiang Electric Power
PublicationYear 2025
Publisher 杭州迈拓大数据服务有限公司,杭州 310007%国网浙江省电力有限公司科技创新中心,杭州 310007
Publisher_xml – name: 杭州迈拓大数据服务有限公司,杭州 310007%国网浙江省电力有限公司科技创新中心,杭州 310007
SSID ssib001129659
ssib000269262
ssib051373757
ssib036436285
ssj0002912195
Score 2.4102488
Snippet 针对现有电力负荷预测模型难以深入提取时空关联特征,模型泛化能力弱,无法同时胜任短期和长期的电力负荷预测的问题,提出一种面向多用户的基于余弦相似度和全局-局部协同图...
SourceID wanfang
SourceType Aggregation Database
StartPage 68
Title 基于余弦相似度和图卷积网络的电力负荷预测方法
URI https://d.wanfangdata.com.cn/periodical/zjdl202501007
Volume 44
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  issn: 1007-1881
  databaseCode: DOA
  dateStart: 20200101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.doaj.org/
  omitProxy: true
  ssIdentifier: ssj0002912195
  providerName: Directory of Open Access Journals
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1NT9RAtCJevBiNGj8JB-dkVtuZznTm2O52gyZ6goQbabtdjYc1keXCmZOKiUZNFBMSD3j0oARF8NdQFv-F771ply4QRZOmeTvvzfvo6-x70_lynBvdnKvE85KG1Fo1_ITjHpBZtxFw3N68kyuRY0fx3n01NePfnZWzY-MnarOWFvrprWzxyHUl_-NVKAO_4irZf_DskCkUAAz-hTt4GO7H8jGLJTNtFoUs9vGuYwJazBhERU0WKhYHzEQs0oRq4oWokFBQnTNNJUgTI6BbLAqwVghXGwFk6BEQMdMkhiDLJwB4SqoVIodYs8hHlQAo-RgWciJWSKkjBAzAhkoEs4dfVvlxSWYs1iNWB6UMJ_3cwe2mhy834kFlY-0LQP4-RiFHNMagJWFU_9bBcVphw66LpreTyFssbJWMTEx2tZnWiAITjCBhPspDYiBzCQW1YippImwVDr2qxJB8uFxCAQfSVbfRO7x5WO5NGhcJGJeVh1o1fxz5pECMd5RjjqGBdbnlDLW0pdFVdUVG-khZqghPRPxJ71rAw0_VnrbH5lQR0e7IOdLybXizJyCViZI98eZQCDbQAaUYvPiog2N7kGN7lcjRnc2RYIg_6ZziEJjd2lcROxCuRna0xO5B7YADAQk1LgKufktPBCIoB_IxGePGg5gsac5DaWk5twH1vH1QS1q61-smvQe1LHP6rHOm7B5Ohratn3PGFh-ed6JidXNn88XO9rtia22w8m1na6vYXCtePS9WfhbLG4NPnwfbLwc_PgzeLw1erxdPV_a-ru4tb_z6uLS7_mz37ffdL28uODPteLo51SjPPmnMk6JpzjPecbtGZonOhc7dXLhJJlIwIJWSq0AlMk91ppVRqWuCLE2CTpd3UpGlygTiojPee9zLLzmTvuhk0E_LAwNdBy0SI0SiJc-0kYlJEn3ZmShtniv_2-bnRlxz5W8EV53T-631mjPef7KQX4dcvZ9OkDd_A2Mpqj8
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E4%BD%99%E5%BC%A6%E7%9B%B8%E4%BC%BC%E5%BA%A6%E5%92%8C%E5%9B%BE%E5%8D%B7%E7%A7%AF%E7%BD%91%E7%BB%9C%E7%9A%84%E7%94%B5%E5%8A%9B%E8%B4%9F%E8%8D%B7%E9%A2%84%E6%B5%8B%E6%96%B9%E6%B3%95&rft.jtitle=%E6%B5%99%E6%B1%9F%E7%94%B5%E5%8A%9B&rft.au=JI+Shan&rft.au=%E5%A7%9C%E5%B7%8D&rft.au=%E6%99%AF%E9%91%AB&rft.date=2025-01-25&rft.pub=%E6%9D%AD%E5%B7%9E%E8%BF%88%E6%8B%93%E5%A4%A7%E6%95%B0%E6%8D%AE%E6%9C%8D%E5%8A%A1%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8%2C%E6%9D%AD%E5%B7%9E+310007%25%E5%9B%BD%E7%BD%91%E6%B5%99%E6%B1%9F%E7%9C%81%E7%94%B5%E5%8A%9B%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8%E7%A7%91%E6%8A%80%E5%88%9B%E6%96%B0%E4%B8%AD%E5%BF%83%2C%E6%9D%AD%E5%B7%9E+310007&rft.issn=1007-1881&rft.volume=44&rft.issue=1&rft.spage=68&rft.epage=75&rft_id=info:doi/10.19585%2Fj.zjdl.202501007&rft.externalDocID=zjdl202501007
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzjdl%2Fzjdl.jpg