A Hybrid Short-Term Load Forecasting Approach for Individual Residential Customer

This article proposes a hybrid method (HM) to improve the accuracy of short-term individual residential load forecasting. The HM includes an ensemble model (EM), deep ensemble model (DEM), and thermal dynamic model expressed by resistance-capacitance (RC). The EM consists of three predictors of supp...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on power delivery Ročník 38; číslo 1; s. 26 - 37
Hlavní autoři: Lin, Xin, Zamora, Ramon, Baguley, Craig A., Srivastava, Anurag K.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.02.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:0885-8977, 1937-4208
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This article proposes a hybrid method (HM) to improve the accuracy of short-term individual residential load forecasting. The HM includes an ensemble model (EM), deep ensemble model (DEM), and thermal dynamic model expressed by resistance-capacitance (RC). The EM consists of three predictors of support vector machine (SVM), back propagation neural network (BPNN), and generalized regression neural network (GRNN). The genetic algorithm (GA) is used to optimize SVM and BPNN to enhance their performance. The DEM includes multiple bi-directional long-short term memory (Bi-LSTM) networks. The Bayesian algorithm (BA) is used to optimize the hyperparameters of the Bi-LSTM. The outputs of individual predictors are aggregated using an optimal trimmed algorithm. At first, the total load is separated into the heater and air conditioning (HAC), and non-HAC loads. Then, the RC model is presented to predict the indoor temperature, which integrates outdoor weather and less HAC historical data as the input of the EM to forecast the HAC load. After that, non-HAC loads are further divided into electric lighting and other loads. A daylight equation is used to calculate the illuminance, which is combined with less lighting historical data as the input of DEM to predict electric lights usage. Then, other loads are captured by DEM through less historical data. Finally, the total load is obtained by combining the predicted HAC and non-HAC loads. The datasets from the UMass Smart Microgrid and Flexhouse projects are used to test the proposed method. The comparison with existing models proves that the presented model can provide accurate short-term individual load forecasting.
AbstractList This article proposes a hybrid method (HM) to improve the accuracy of short-term individual residential load forecasting. The HM includes an ensemble model (EM), deep ensemble model (DEM), and thermal dynamic model expressed by resistance-capacitance (RC). The EM consists of three predictors of support vector machine (SVM), back propagation neural network (BPNN), and generalized regression neural network (GRNN). The genetic algorithm (GA) is used to optimize SVM and BPNN to enhance their performance. The DEM includes multiple bi-directional long-short term memory (Bi-LSTM) networks. The Bayesian algorithm (BA) is used to optimize the hyperparameters of the Bi-LSTM. The outputs of individual predictors are aggregated using an optimal trimmed algorithm. At first, the total load is separated into the heater and air conditioning (HAC), and non-HAC loads. Then, the RC model is presented to predict the indoor temperature, which integrates outdoor weather and less HAC historical data as the input of the EM to forecast the HAC load. After that, non-HAC loads are further divided into electric lighting and other loads. A daylight equation is used to calculate the illuminance, which is combined with less lighting historical data as the input of DEM to predict electric lights usage. Then, other loads are captured by DEM through less historical data. Finally, the total load is obtained by combining the predicted HAC and non-HAC loads. The datasets from the UMass Smart Microgrid and Flexhouse projects are used to test the proposed method. The comparison with existing models proves that the presented model can provide accurate short-term individual load forecasting.
Author Lin, Xin
Zamora, Ramon
Srivastava, Anurag K.
Baguley, Craig A.
Author_xml – sequence: 1
  givenname: Xin
  orcidid: 0000-0003-3971-9015
  surname: Lin
  fullname: Lin, Xin
  email: xin.lin@aut.ac.nz
  organization: Electrical and Electronic Engineering Department, Auckland University of Technology, Auckland, New Zealand
– sequence: 2
  givenname: Ramon
  orcidid: 0000-0002-1269-8368
  surname: Zamora
  fullname: Zamora, Ramon
  email: ramon.zamora@aut.ac.nz
  organization: Electrical and Electronic Engineering Department, Auckland University of Technology, Auckland, New Zealand
– sequence: 3
  givenname: Craig A.
  orcidid: 0000-0003-1673-5792
  surname: Baguley
  fullname: Baguley, Craig A.
  email: craig.baguley@aut.ac.nz
  organization: Electrical and Electronic Engineering Department, Auckland University of Technology, Auckland, New Zealand
– sequence: 4
  givenname: Anurag K.
  orcidid: 0000-0003-3518-8018
  surname: Srivastava
  fullname: Srivastava, Anurag K.
  email: anurag.srivastava@mail.wvu.edu
  organization: Computer Science and Electrical Engineering Department, West Virginia University, Morgantown, WV, USA
BookMark eNp9kE1PAjEQhhuDiYD-Ab008bw47X60PRIUISFREeNx0227UgJbbIsJ_95FiAcPnmYO7zPv5OmhTuMag9A1gQEhIO4Wz-_z-wEFSgcpYZxTeoa6RKQsySjwDuoC53nCBWMXqBfCCgAyENBFL0M82Vfeavy6dD4mC-M3eOakxmPnjZIh2uYDD7db76Ra4tp5PG20_bJ6J9d4boLVpom23Ue7EN3G-Et0Xst1MFen2Udv44fFaJLMnh6no-EsUVTkMckF50WeMlGxShe5qrNKVKrgKpOccCFpTYipSZbmSishU-BAayg4VEYVGlTaR7fHu-1rnzsTYrlyO9-0lSVlhUiFKFjepugxpbwLwZu63Hq7kX5fEigP6sofdeVBXXlS10L8D6RslNG6Jnpp1_-jN0fUGmN-uwTjmYAi_Qb75X43
CODEN ITPDE5
CitedBy_id crossref_primary_10_1016_j_egyr_2024_06_010
crossref_primary_10_1109_TPWRS_2024_3431880
crossref_primary_10_3390_su16166903
crossref_primary_10_1016_j_measurement_2024_114223
crossref_primary_10_1186_s40807_025_00192_w
crossref_primary_10_1109_ACCESS_2023_3276646
crossref_primary_10_1109_TPWRD_2025_3576589
crossref_primary_10_1109_TPWRD_2025_3545638
crossref_primary_10_1016_j_apenergy_2025_125977
crossref_primary_10_1016_j_engappai_2025_110980
crossref_primary_10_1088_1742_6596_2781_1_012025
crossref_primary_10_1177_14727978251364418
crossref_primary_10_1109_TPWRD_2024_3486010
crossref_primary_10_1109_ACCESS_2023_3323403
crossref_primary_10_3390_pr11102981
crossref_primary_10_1088_1742_6596_3043_1_012149
crossref_primary_10_1016_j_ymssp_2023_111058
crossref_primary_10_1049_gtd2_13140
crossref_primary_10_1016_j_energy_2025_135854
crossref_primary_10_1109_TPWRD_2024_3496998
crossref_primary_10_1109_TTE_2024_3422993
crossref_primary_10_1016_j_est_2025_116874
crossref_primary_10_1016_j_rineng_2025_105800
crossref_primary_10_1016_j_ijepes_2025_111065
crossref_primary_10_1109_TNSM_2024_3470853
crossref_primary_10_3390_electronics12163441
crossref_primary_10_1016_j_jobe_2024_108917
crossref_primary_10_1007_s40866_023_00188_9
Cites_doi 10.1109/TSG.2018.2818167
10.1016/j.apenergy.2017.12.051
10.1109/TPWRS.2018.2872388
10.1109/TIE.2019.2939988
10.1109/TIE.2015.2424399
10.1016/j.applthermaleng.2019.04.040
10.1109/TSTE.2018.2883393
10.1016/j.solener.2020.03.104
10.1109/JSYST.2018.2890524
10.1109/PESGM.2014.6939378
10.1109/TPWRS.2020.3042389
10.1109/ACCESS.2020.2982366
10.1109/TII.2017.2789289
10.1109/TITS.2018.2867042
10.1002/0470024275.app7
10.1109/TSG.2017.2753802
10.35833/MPCE.2020.000004
10.1007/s42835-019-00289-5
10.1109/ISGT-Asia.2016.7796484
10.1016/j.energy.2019.116552
10.1109/ACCESS.2020.3027061
10.1016/j.rser.2013.03.004
10.1016/j.energy.2020.118265
10.1109/TSG.2017.2686012
10.1016/j.ijepes.2013.10.020
10.1016/j.enbuild.2018.06.050
10.1109/ACCESS.2020.3028281
10.1109/TII.2020.3000184
10.1109/TSTE.2019.2931154
10.1016/j.enbuild.2018.01.039
10.1109/ACCESS.2021.3053069
10.1061/(ASCE)AE.1943-5568.0000183
10.1016/j.ijepes.2014.08.025
10.1109/TPWRD.2014.2386696
10.1016/j.rser.2021.110788
10.1016/j.enbuild.2016.02.030
10.1016/j.solener.2007.04.008
10.1016/j.scs.2019.101533
10.1109/ACCESS.2020.2994119
10.1016/j.enbuild.2015.09.033
10.1109/TIE.2020.3009604
10.1109/TSG.2017.2743015
10.1109/TII.2018.2871159
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
7TB
8FD
FR3
KR7
L7M
DOI 10.1109/TPWRD.2022.3178822
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Civil Engineering Abstracts
Engineering Research Database
Technology Research Database
Mechanical & Transportation Engineering Abstracts
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Civil Engineering Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1937-4208
EndPage 37
ExternalDocumentID 10_1109_TPWRD_2022_3178822
9784906
Genre orig-research
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACKIV
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
TWZ
VH1
VJK
AAYXX
CITATION
7SP
7TB
8FD
FR3
KR7
L7M
ID FETCH-LOGICAL-c295t-598865379b7bd65cf4b9bc68c4a8189a2f11ef1435cdc9a30802f0680bec6d0c3
IEDL.DBID RIE
ISICitedReferencesCount 36
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000966947400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0885-8977
IngestDate Mon Jun 30 02:41:56 EDT 2025
Tue Nov 18 22:07:02 EST 2025
Sat Nov 29 01:38:14 EST 2025
Wed Aug 27 02:18:16 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c295t-598865379b7bd65cf4b9bc68c4a8189a2f11ef1435cdc9a30802f0680bec6d0c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-1673-5792
0000-0003-3518-8018
0000-0003-3971-9015
0000-0002-1269-8368
PQID 2769399675
PQPubID 85445
PageCount 12
ParticipantIDs ieee_primary_9784906
proquest_journals_2769399675
crossref_primary_10_1109_TPWRD_2022_3178822
crossref_citationtrail_10_1109_TPWRD_2022_3178822
PublicationCentury 2000
PublicationDate 2023-02-01
PublicationDateYYYYMMDD 2023-02-01
PublicationDate_xml – month: 02
  year: 2023
  text: 2023-02-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on power delivery
PublicationTitleAbbrev TPWRD
PublicationYear 2023
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
ref35
ref12
ref15
(ref33) 2022
ref37
ref14
ref36
ref31
ref30
ref11
ref10
ref32
ref2
ref1
ref17
ref39
ref16
ref38
ref19
ref18
(ref47) 2021
ref24
ref23
ref45
ref26
ref48
ref25
ref20
ref42
ref41
ref22
ref21
ref43
Thavlov (ref34) 2008
ref28
ref27
ref29
ref8
Brochu (ref44) 2010
ref7
ref9
ref4
ref3
ref6
ref5
(ref46) 2021
ref40
References_xml – ident: ref15
  doi: 10.1109/TSG.2018.2818167
– ident: ref11
  doi: 10.1016/j.apenergy.2017.12.051
– ident: ref12
  doi: 10.1109/TPWRS.2018.2872388
– ident: ref20
  doi: 10.1109/TIE.2019.2939988
– ident: ref16
  doi: 10.1109/TIE.2015.2424399
– year: 2008
  ident: ref34
  article-title: Dynamic optimization of power consumption
– ident: ref19
  doi: 10.1016/j.applthermaleng.2019.04.040
– ident: ref22
  doi: 10.1109/TSTE.2018.2883393
– ident: ref36
  doi: 10.1016/j.solener.2020.03.104
– ident: ref28
  doi: 10.1109/JSYST.2018.2890524
– ident: ref9
  doi: 10.1109/PESGM.2014.6939378
– ident: ref23
  doi: 10.1109/TPWRS.2020.3042389
– year: 2021
  ident: ref47
  article-title: Data and experiments for building energy performance
– ident: ref39
  doi: 10.1109/ACCESS.2020.2982366
– ident: ref40
  doi: 10.1109/TII.2017.2789289
– ident: ref42
  doi: 10.1109/TITS.2018.2867042
– ident: ref38
  doi: 10.1002/0470024275.app7
– ident: ref3
  doi: 10.1109/TSG.2017.2753802
– ident: ref41
  doi: 10.35833/MPCE.2020.000004
– ident: ref17
  doi: 10.1007/s42835-019-00289-5
– ident: ref8
  doi: 10.1109/ISGT-Asia.2016.7796484
– ident: ref5
  doi: 10.1016/j.energy.2019.116552
– ident: ref26
  doi: 10.1109/ACCESS.2020.3027061
– ident: ref27
  doi: 10.1016/j.rser.2013.03.004
– ident: ref6
  doi: 10.1016/j.energy.2020.118265
– ident: ref7
  doi: 10.1109/TSG.2017.2686012
– ident: ref18
  doi: 10.1016/j.ijepes.2013.10.020
– year: 2010
  ident: ref44
  article-title: A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning
– ident: ref14
  doi: 10.1016/j.enbuild.2018.06.050
– ident: ref10
  doi: 10.1109/ACCESS.2020.3028281
– ident: ref1
  doi: 10.1109/TII.2020.3000184
– ident: ref21
  doi: 10.1109/TSTE.2019.2931154
– ident: ref30
  doi: 10.1016/j.enbuild.2018.01.039
– ident: ref2
  doi: 10.1109/ACCESS.2021.3053069
– ident: ref32
  doi: 10.1061/(ASCE)AE.1943-5568.0000183
– ident: ref45
  doi: 10.1016/j.ijepes.2014.08.025
– ident: ref13
  doi: 10.1109/TPWRD.2014.2386696
– ident: ref24
  doi: 10.1016/j.rser.2021.110788
– ident: ref35
  doi: 10.1016/j.enbuild.2016.02.030
– ident: ref37
  doi: 10.1016/j.solener.2007.04.008
– ident: ref29
  doi: 10.1016/j.scs.2019.101533
– ident: ref25
  doi: 10.1109/ACCESS.2020.2994119
– ident: ref31
  doi: 10.1016/j.enbuild.2015.09.033
– year: 2021
  ident: ref46
  article-title: Umass smart dataset
– ident: ref43
  doi: 10.1109/TIE.2020.3009604
– ident: ref4
  doi: 10.1109/TSG.2017.2743015
– year: 2022
  ident: ref33
  article-title: Energy use in homes
– ident: ref48
  doi: 10.1109/TII.2018.2871159
SSID ssj0004090
Score 2.5457878
Snippet This article proposes a hybrid method (HM) to improve the accuracy of short-term individual residential load forecasting. The HM includes an ensemble model...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 26
SubjectTerms Air conditioning
Algorithms
Artificial neural networks
Atmospheric modeling
Back propagation networks
Bayesian algorithm
Bi-LSTM
BPNN
Data models
Distributed generation
Dynamic models
Electrical loads
Forecasting
genetic algorithm
Genetic algorithms
GRNN
hybrid method
Illuminance
Lighting
Load
Load modeling
Neural networks
Optimization
Predictive models
short-term residential load forecasting
Support vector machines
SVM
thermal dynamic model
trimmed algorithm
Title A Hybrid Short-Term Load Forecasting Approach for Individual Residential Customer
URI https://ieeexplore.ieee.org/document/9784906
https://www.proquest.com/docview/2769399675
Volume 38
WOSCitedRecordID wos000966947400001&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1937-4208
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004090
  issn: 0885-8977
  databaseCode: RIE
  dateStart: 19860101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5zeNCDv6Y4nZKDN422XdIkxzEdE8aYc-JuJU1SFGYn-yH435vXdlVRBG89JFDymve-l-b7PoTOLHM1IUwYYcJTxOF_SgRlhnDwKA9srLSfEYV7vN8X47EcVNBFyYWx1maXz-wlPGb_8s1UL-GoDNRgqQR97TXOw5yr9cmB9PLzFCEYEQ7UrAgynrwaDR6H164VDALXobqWLwi-FaHMVeVHKs7qS2f7f2-2g7YKHIlbeeB3UcWme2jzi7pgDd21cPcdCFn4_smBbDJySRj3pspg8OPUag43nnGrEBXHDr3i25KehYcWjDxTlwAmuL10EPHFzvbRQ-dm1O6SwkGB6ECyBWFSiJA1uYx5bEKmExrLWIdCU-UKtVRB4vs2AcikjZaqCcTbBNw4XGRD4-nmAaqm09QeIuzHnMoEFKeURw3TwiFD6hnLaaI8bUwd-asljXQhLw4uF5MoazM8GWVhiCAMURGGOjov57zm4hp_jq7BwpcjizWvo8YqclGx_-ZRABaPrpXj7Oj3WcdoA4zj8_vXDVRdzJb2BK3rt8XzfHaafVofI3jKnA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT-MwEB1VgAR74GMLosvH-sANDI5rJ_axKqAiuhWwXS23yLEdgVTaVT9W4t_jSdIuKxAStxxsKfLEM28cv_cAjrwMNSHOJZWKGRrwv6BKSEcT9CjnPjM2KojC3aTXU_f3-qYGJwsujPe-uHzmT_Gx-JfvRnaGR2WoBis06msvSyE4K9la_1iQrDxRUUpSFWDNnCLD9Fn_5vfdeWgGOQ89amj6OP-vDBW-Km-ScVFhLjc-926bsF4hSdIqQ78FNT_8Cl9e6QvW4bZFOs9IySI_HwLMpv2Qhkl3ZBxBR05rJnjnmbQqWXES8Cu5WhC0yJ1HK89hSAED0p4FkPjkx9vw6_Ki3-7QykOBWq7llEqtVCybic6SzMXS5iLTmY2VFSaUam14HkU-R9BkndWmidTbHP04Qmxjx2xzB5aGo6HfBRJlidA5ak4ZJpy0KmBDwZxPRG6Yda4B0XxJU1sJjKPPxSAtGg2m0yIMKYYhrcLQgOPFnD-lvMaHo-u48IuR1Zo3YH8eubTagZOUo8ljaOYS-e39Wd9htdP_0U27V73rPVhDG_nyNvY-LE3HM38AK_bv9HEyPiw-sxfX283j
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=A+Hybrid+Short-Term+Load+Forecasting+Approach+for+Individual+Residential+Customer&rft.jtitle=IEEE+transactions+on+power+delivery&rft.au=Lin%2C+Xin&rft.au=Zamora%2C+Ramon&rft.au=Baguley%2C+Craig+A&rft.au=Srivastava%2C+Anurag+K&rft.date=2023-02-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0885-8977&rft.eissn=1937-4208&rft.volume=38&rft.issue=1&rft.spage=26&rft_id=info:doi/10.1109%2FTPWRD.2022.3178822&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0885-8977&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0885-8977&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0885-8977&client=summon