Missing-Insensitive Short-Term Load Forecasting Leveraging Autoencoder and LSTM

In most deep learning-based load forecasting, an intact dataset is required. Since many real-world datasets contain missing values for various reasons, missing imputation using deep learning is actively studied. However, missing imputation and load forecasting have been considered independently so f...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 8; pp. 206039 - 206048
Main Authors: Park, Kyungnam, Jeong, Jaeik, Kim, Dongjoo, Kim, Hongseok
Format: Journal Article
Language:English
Published: Piscataway IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In most deep learning-based load forecasting, an intact dataset is required. Since many real-world datasets contain missing values for various reasons, missing imputation using deep learning is actively studied. However, missing imputation and load forecasting have been considered independently so far. In this article, we provide a deep learning framework that jointly considers missing imputation and load forecasting. We consider a family of autoencoder/long short-term memory (LSTM) combined models for missing-insensitive load forecasting. Specifically, autoencoder (AE), denoising autoencoder (DAE), convolutional autoencoder (CAE), and denoising convolutional autoencoder (DCAE) are considered for extracting features, of which the encoded outputs are fed into the input of LSTM. Our experiments show that the proposed DCAE/LSTM combined model significantly improves forecasting accuracy no matter what missing rate or type (random missing, consecutive block missing) occurs compared to the baseline LSTM.
AbstractList In most deep learning-based load forecasting, an intact dataset is required. Since many real-world datasets contain missing values for various reasons, missing imputation using deep learning is actively studied. However, missing imputation and load forecasting have been considered independently so far. In this article, we provide a deep learning framework that jointly considers missing imputation and load forecasting. We consider a family of autoencoder/long short-term memory (LSTM) combined models for missing-insensitive load forecasting. Specifically, autoencoder (AE), denoising autoencoder (DAE), convolutional autoencoder (CAE), and denoising convolutional autoencoder (DCAE) are considered for extracting features, of which the encoded outputs are fed into the input of LSTM. Our experiments show that the proposed DCAE/LSTM combined model significantly improves forecasting accuracy no matter what missing rate or type (random missing, consecutive block missing) occurs compared to the baseline LSTM.
Author Kim, Hongseok
Park, Kyungnam
Jeong, Jaeik
Kim, Dongjoo
Author_xml – sequence: 1
  givenname: Kyungnam
  orcidid: 0000-0003-2817-2974
  surname: Park
  fullname: Park, Kyungnam
  organization: Department of Electronic Engineering, Sogang University, Seoul, South Korea
– sequence: 2
  givenname: Jaeik
  orcidid: 0000-0002-5796-8106
  surname: Jeong
  fullname: Jeong, Jaeik
  organization: Department of Electronic Engineering, Sogang University, Seoul, South Korea
– sequence: 3
  givenname: Dongjoo
  orcidid: 0000-0002-8924-257X
  surname: Kim
  fullname: Kim, Dongjoo
  organization: Smart Power Distribution Laboratory, Korea Power Electric Corporation (KEPCO) Research Institute, Daejeon, South Korea
– sequence: 4
  givenname: Hongseok
  orcidid: 0000-0002-5744-2358
  surname: Kim
  fullname: Kim, Hongseok
  email: hongseok@sogang.ac.kr
  organization: Department of Electronic Engineering, Sogang University, Seoul, South Korea
BookMark eNp9kUFrGzEQhUVJoWmaX5DLQs_rSBppVzoak7SGDTnYPQutduTKOKtUkgP591l3k1JyyFxmGN73ePC-krMxjkjIFaMLxqi-Xq5WN5vNglNOF0ChUUp-IuecNboGCc3Zf_cXcpnznk6jppdsz8n9Xcg5jLt6PWYccyjhCavN75hKvcX0UHXRDtVtTOhsLpOu6vAJk92dzuWxRBxdHDBVdhyqbrO9-0Y-e3vIePm6L8iv25vt6mfd3f9Yr5Zd7QRVpYZBCuilh9ZppNCD9Y7JBhA9o8h0D0A96kZrRanQ1lrackSQmvdSWA8XZD37DtHuzWMKDzY9m2iD-fuIaWdsKsEd0EzeyinuNAMqQMnes1613rd2oI2gbvL6Pns9pvjniLmYfTymcYpvuGi4kkLQdlLpWeVSzDmhNy4UW0IcS7LhYBg1pzrMXIc51WFe65hYeMe-Jf6YupqpgIj_CM0lVwrgBT6BlyQ
CODEN IAECCG
CitedBy_id crossref_primary_10_1007_s40095_022_00480_x
crossref_primary_10_3390_en18184867
crossref_primary_10_1109_TSG_2022_3158387
crossref_primary_10_1109_ACCESS_2024_3357533
crossref_primary_10_1016_j_eswa_2024_124507
crossref_primary_10_3390_electronics14071383
crossref_primary_10_1109_ACCESS_2023_3233951
crossref_primary_10_1016_j_apenergy_2023_122146
crossref_primary_10_3390_en15239125
crossref_primary_10_1016_j_apenergy_2024_123757
crossref_primary_10_1109_ACCESS_2021_3061370
crossref_primary_10_1109_ACCESS_2023_3262026
crossref_primary_10_3390_en16247933
crossref_primary_10_1016_j_enbuild_2025_115383
Cites_doi 10.1109/ACCESS.2020.2976500
10.1109/59.651623
10.1109/TSP.2019.2944758
10.1109/TSG.2018.2807845
10.1109/ACCESS.2017.2740968
10.1007/978-1-4842-4470-8_7
10.1109/ACCESS.2018.2875742
10.1109/TSG.2016.2628061
10.1109/TPWRS.2009.2030426
10.1109/TPWRS.2017.2688178
10.1016/j.ejor.2018.12.013
10.1109/ACCESS.2018.2803755
10.1016/j.neunet.2009.11.014
10.1016/j.apenergy.2019.113500
10.3390/en10010003
10.1109/TPWRS.2019.2936293
10.1109/SmartGridComm.2018.8587554
10.1109/TITS.2018.2869768
10.1109/TII.2017.2789297
10.1109/TII.2019.2942353
10.1007/BF01421959
10.1109/TPWRS.2018.2847289
10.1109/IWCIA.2016.7805741
10.1109/ACCESS.2020.2968939
10.1109/TPWRS.2018.2872388
10.1038/s41598-018-34688-x
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
DOA
DOI 10.1109/ACCESS.2020.3036885
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
METADEX
Computer and Information Systems Abstracts Professional
DatabaseTitleList Materials Research Database


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 206048
ExternalDocumentID oai_doaj_org_article_3af8c82c91304385bf1b87ff7ad0640c
10_1109_ACCESS_2020_3036885
9252883
Genre orig-research
GrantInformation_xml – fundername: Korea Institute of Energy Technology Evaluation and Planning (KETEP)
  funderid: 10.13039/501100007053
– fundername: Ministry of Trade, Industry and Energy (MOTIE), South Korea
  grantid: 20192010107290
  funderid: 10.13039/501100003052
– fundername: Smart City Research and Development project of the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure, and Transport
  grantid: 19NSPS-B152996-02
  funderid: 10.13039/501100007694
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
AGSQL
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c408t-3d543b5f37c9e03b3afc1563eef10e19b330fe969980049aaa072ee3592b54af3
IEDL.DBID RIE
ISICitedReferencesCount 18
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000592103300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:50:41 EDT 2025
Sun Jun 29 12:47:48 EDT 2025
Tue Nov 18 22:19:48 EST 2025
Sat Nov 29 04:14:25 EST 2025
Wed Aug 27 02:27:43 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c408t-3d543b5f37c9e03b3afc1563eef10e19b330fe969980049aaa072ee3592b54af3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8924-257X
0000-0003-2817-2974
0000-0002-5796-8106
0000-0002-5744-2358
OpenAccessLink https://ieeexplore.ieee.org/document/9252883
PQID 2462854407
PQPubID 4845423
PageCount 10
ParticipantIDs ieee_primary_9252883
crossref_primary_10_1109_ACCESS_2020_3036885
proquest_journals_2462854407
doaj_primary_oai_doaj_org_article_3af8c82c91304385bf1b87ff7ad0640c
crossref_citationtrail_10_1109_ACCESS_2020_3036885
PublicationCentury 2000
PublicationDate 20200000
2020-00-00
20200101
2020-01-01
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – year: 2020
  text: 20200000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
PublicationYear 2020
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
lóez (ref3) 2019; 34
ref12
ref15
ref14
ref31
ref11
ref10
ref2
ref1
ref17
ref16
ref19
ref18
asadi (ref21) 2019
hwang (ref25) 2017
ref24
ref23
lipton (ref30) 2016
ref26
ref20
ref22
ref27
ref8
ref7
abadi (ref28) 2016; 16
ref9
ref4
ref6
kingma (ref29) 2015
ref5
References_xml – ident: ref16
  doi: 10.1109/ACCESS.2020.2976500
– ident: ref11
  doi: 10.1109/59.651623
– ident: ref17
  doi: 10.1109/TSP.2019.2944758
– start-page: 1
  year: 2015
  ident: ref29
  article-title: Adam: A method for stochastic optimization
  publication-title: Proc Int Conf Learn Represent
– ident: ref8
  doi: 10.1109/TSG.2018.2807845
– ident: ref26
  doi: 10.1109/ACCESS.2017.2740968
– ident: ref31
  doi: 10.1007/978-1-4842-4470-8_7
– ident: ref22
  doi: 10.1109/ACCESS.2018.2875742
– ident: ref7
  doi: 10.1109/TSG.2016.2628061
– ident: ref5
  doi: 10.1109/TPWRS.2009.2030426
– ident: ref27
  doi: 10.1109/TPWRS.2017.2688178
– year: 2017
  ident: ref25
  article-title: Adversarial training for disease prediction from electronic health records with missing data
  publication-title: arXiv 1711 04126
– volume: 16
  start-page: 265
  year: 2016
  ident: ref28
  article-title: TensorFlow: A system for large-scale machine learning
  publication-title: Proc OSDI
– ident: ref2
  doi: 10.1016/j.ejor.2018.12.013
– ident: ref23
  doi: 10.1109/ACCESS.2018.2803755
– ident: ref15
  doi: 10.1016/j.neunet.2009.11.014
– ident: ref1
  doi: 10.1016/j.apenergy.2019.113500
– ident: ref10
  doi: 10.3390/en10010003
– ident: ref18
  doi: 10.1109/TPWRS.2019.2936293
– ident: ref13
  doi: 10.1109/SmartGridComm.2018.8587554
– ident: ref14
  doi: 10.1109/TITS.2018.2869768
– ident: ref6
  doi: 10.1109/TII.2017.2789297
– year: 2019
  ident: ref21
  article-title: A convolution recurrent autoencoder for spatio-temporal missing data imputation
  publication-title: arXiv 1904 12413
– ident: ref9
  doi: 10.1109/TII.2019.2942353
– year: 2016
  ident: ref30
  article-title: Directly modeling missing data in sequences with RNNs: Improved classification of clinical time series
  publication-title: arXiv 1606 04130
– ident: ref19
  doi: 10.1007/BF01421959
– ident: ref4
  doi: 10.1109/TPWRS.2018.2847289
– ident: ref24
  doi: 10.1109/IWCIA.2016.7805741
– ident: ref12
  doi: 10.1109/ACCESS.2020.2968939
– volume: 34
  start-page: 1427
  year: 2019
  ident: ref3
  article-title: Parsimonious short-term load forecasting for optimal operation planning of electrical distribution systems
  publication-title: IEEE Trans Power Syst
  doi: 10.1109/TPWRS.2018.2872388
– ident: ref20
  doi: 10.1038/s41598-018-34688-x
SSID ssj0000816957
Score 2.2951899
Snippet In most deep learning-based load forecasting, an intact dataset is required. Since many real-world datasets contain missing values for various reasons, missing...
SourceID doaj
proquest
crossref
ieee
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 206039
SubjectTerms Datasets
Deep learning
Feature extraction
Forecasting
Load forecasting
Load modeling
Mathematical models
Missing data
missing data imputation
Model accuracy
Noise reduction
Predictive models
short-term load forecasting
Time series analysis
Training
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PaxQxFA5SetCDWKu4WiUHj4ZmJslM3nG7tFTYVqGr9BbyEwXZLbtb_37fy0yXBaFevA1DMjP58uYlXybzfYx9xDG3y11nhI_QCZ06JcDYLJKF4KGEMizmfJ_319f29ha-7ll90Z6wQR54AO5U-WKjbSNgstXKmlCaYPtSep_oI1Sk7Ct72CNTNQfbpgPTjzJDjYTT6WyGLUJC2CJPxbRtyT15byiqiv2jxcpfebkONhcv2PNxlsinw9MdsSd5-ZI929MOPGZfrhAyPBKfaXV4U7cA8ZsfOJsWC8y2fL7yiZPxZvQb2trM5xmjtnoS8en9dkUClimvuV8mPr9ZXL1i3y7OF7NLMbojiKil3QqVjFbBFNVHyFIFBCoiGVM5l0bmBoJSsmTokE8RDfDey77NWRlog9G-qNfsYLla5jeMtyrlPmkdEWitsFL0ofGyoRrgQU1Y-wCUi6N0ODlY_HKVQkhwA7qO0HUjuhP2aVfpblDOeLz4GfXArijJXtcTGAxuDAb3r2CYsGPqv91FoDXkpjxhJw_96cZXdONaXf8eRUL79n_c-h17Ss0ZVmdO2MF2fZ_fs8P4e_tzs_5Qo_MPIVTlHg
  priority: 102
  providerName: Directory of Open Access Journals
Title Missing-Insensitive Short-Term Load Forecasting Leveraging Autoencoder and LSTM
URI https://ieeexplore.ieee.org/document/9252883
https://www.proquest.com/docview/2462854407
https://doaj.org/article/3af8c82c91304385bf1b87ff7ad0640c
Volume 8
WOSCitedRecordID wos000592103300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1baxQxFA5t8UEfvFVxtZY8-NjYmUkySR7XpUVhtwpdpW8hlxMUZFf24qO_3ZNMOhQUwZchDDlDki-X-U6S8xHyBtfcHvpeMhdMz0TsOTNSA4vaeGeST4Mz58tcXV3pmxvz6YCcjXdhAKAcPoO3OVn28uM67LOr7Nx0MovjHpJDpfrhrtboT8kCEkaqGliobcz5dDbDOiAF7JCZ4kSts17yncWnxOivoip_zMRlebl89H8Fe0we1t9IOh1wf0IOYPWUPLgTXPCYfFxgm2KKfcju4205I0Svv-LvNlvidEznaxdpVuYMbpvPPtM5YLcuokV0ut-tc4TLCBvqVpHOr5eLZ-Tz5cVy9p5V-QQWRKN3jEcpuJeJq2Cg4Z67FJCtcYDUNtAaz3mTwPRIuDJPcM41qgPg0nReCpf4c3K0Wq_gBaEdj6CiECHoTnA0Cs63rmmzhXGGT0h326421NjiWeLiuy0cozF2AMNmMGwFY0LORqMfQ2iNf2d_lwEbs-a42OUFImHrMLNYR41lDAaXZsG19Kn1WqWkXMxblmFCjjN640cqcBNycgu_rWN4aztRrpci4335d6tX5H4u4OCQOSFHu80eXpN74efu23ZzWtg9Phe_Lk5LV_0N66TkTw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dbxQhEJ_UaqI--FWNp1V58LFYlo9deDwvNm3cO016mr4RFoZoYu7Mffj3C-x200Rj4hvZMBvgBwwzDPMDeJt0bo11rajzpqYy1IIapZEGbTpnYhd7Z87Xtlks9NWV-XwAJ-NbGEQswWf4LhfLXX5Y-312lZ0arjI57i24raTkrH-tNXpUMoWEUc2QWqhi5nQ6m6VeJCOQJ9s0bdU6MybfUD8lS_9Aq_LHXlwUzNnD_2vaI3gwHCTJtEf-MRzg6gncv5Fe8Ag-zdOophK9yA7kbYkSIpff0oGbLtOGTNq1CyRzc3q3zdHPpMU0sQttEZnud-uc4zLghrhVIO3lcv4Uvpx9WM7O6UCgQL1kekdFUFJ0KorGG2SiEy76ZK8JxFgxrEwnBIto6mRyZUvBOccajiiU4Z2SLopncLhar_A5EC4CNkFK7zWXIgl511WOVVnCOCMmwK_H1fohu3gmufhhi5XBjO3BsBkMO4AxgZNR6GefXOPf1d9nwMaqOTN2-ZCQsMNCs6mPOrXRm6ScpdCqi1WnmxgbF_KlpZ_AUUZv_MkA3ASOr-G3wyreWi7LA9Nk8774u9QbuHu-nLe2vVh8fAn3cmN798wxHO42e3wFd_yv3fft5nWZqr8BLjrlcA
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=Missing-Insensitive+Short-Term+Load+Forecasting+Leveraging+Autoencoder+and+LSTM&rft.jtitle=IEEE+access&rft.au=Park%2C+Kyungnam&rft.au=Jeong%2C+Jaeik&rft.au=Kim%2C+Dongjoo&rft.au=Kim%2C+Hongseok&rft.date=2020&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=8&rft.spage=206039&rft.epage=206048&rft_id=info:doi/10.1109%2FACCESS.2020.3036885&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2020_3036885
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon