Conformalized temporal convolutional quantile regression networks for wind power interval forecasting

Wind power interval prediction is an effective technique for quantifying forecasting uncertainty caused by the intermittent and fluctuant characteristics of wind energy. Valid coverage and short interval length are the two most critical targets in interval prediction to attain reliable and accurate...

Full description

Saved in:
Bibliographic Details
Published inEnergy (Oxford) Vol. 248; p. 123497
Main Authors Hu, Jianming, Luo, Qingxi, Tang, Jingwei, Heng, Jiani, Deng, Yuwen
Format Journal Article
LanguageEnglish
Published Oxford Elsevier Ltd 01.06.2022
Elsevier BV
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Wind power interval prediction is an effective technique for quantifying forecasting uncertainty caused by the intermittent and fluctuant characteristics of wind energy. Valid coverage and short interval length are the two most critical targets in interval prediction to attain reliable and accurate information, providing effective support for decision-makers to better control the risks in the power planning. This paper proposes a novel interval prediction approach named conformalized temporal convolutional quantile regression networks (CTCQRN) which combines the conformalized quantile regression (CQR) algorithm with a temporal convolutional network (TCN), without making any distributional assumptions. The proposed model inherits the advantages of quantile regression and conformal prediction that is fully adaptive to heteroscedasticity implicated in data, and meets the theoretical guarantee of valid coverage. As opposed to conventional RNN-based approaches, the adopted TCN architecture frees from suffering iterative propagation and gradient vanishing/explosion, and can handle very long sequences in a parallel manner. Case studies on two different geographical wind power datasets show that the proposed model has a distinct edge over benchmark models in goals of valid coverage and narrow interval bandwidth, which can help to ensure the economic and secure operation of the electric power system. •A novel interval prediction model for wind power is proposed.•The TCN architecture is used to output the initial upper and lower bounds of the prediction intervals (PIs).•The conformalized quantile regression (CQR) algorithm is applied to calibrate the original prediction interval.•The proposal is adaptive to heteroscedasticity and shortens the generated PIs while satisfying the coverage requirement.
AbstractList Wind power interval prediction is an effective technique for quantifying forecasting uncertainty caused by the intermittent and fluctuant characteristics of wind energy. Valid coverage and short interval length are the two most critical targets in interval prediction to attain reliable and accurate information, providing effective support for decision-makers to better control the risks in the power planning. This paper proposes a novel interval prediction approach named conformalized temporal convolutional quantile regression networks (CTCQRN) which combines the conformalized quantile regression (CQR) algorithm with a temporal convolutional network (TCN), without making any distributional assumptions. The proposed model inherits the advantages of quantile regression and conformal prediction that is fully adaptive to heteroscedasticity implicated in data, and meets the theoretical guarantee of valid coverage. As opposed to conventional RNN-based approaches, the adopted TCN architecture frees from suffering iterative propagation and gradient vanishing/explosion, and can handle very long sequences in a parallel manner. Case studies on two different geographical wind power datasets show that the proposed model has a distinct edge over benchmark models in goals of valid coverage and narrow interval bandwidth, which can help to ensure the economic and secure operation of the electric power system. •A novel interval prediction model for wind power is proposed.•The TCN architecture is used to output the initial upper and lower bounds of the prediction intervals (PIs).•The conformalized quantile regression (CQR) algorithm is applied to calibrate the original prediction interval.•The proposal is adaptive to heteroscedasticity and shortens the generated PIs while satisfying the coverage requirement.
Wind power interval prediction is an effective technique for quantifying forecasting uncertainty caused by the intermittent and fluctuant characteristics of wind energy. Valid coverage and short interval length are the two most critical targets in interval prediction to attain reliable and accurate information, providing effective support for decision-makers to better control the risks in the power planning. This paper proposes a novel interval prediction approach named conformalized temporal convolutional quantile regression networks (CTCQRN) which combines the conformalized quantile regression (CQR) algorithm with a temporal convolutional network (TCN), without making any distributional assumptions. The proposed model inherits the advantages of quantile regression and conformal prediction that is fully adaptive to heteroscedasticity implicated in data, and meets the theoretical guarantee of valid coverage. As opposed to conventional RNN-based approaches, the adopted TCN architecture frees from suffering iterative propagation and gradient vanishing/explosion, and can handle very long sequences in a parallel manner. Case studies on two different geographical wind power datasets show that the proposed model has a distinct edge over benchmark models in goals of valid coverage and narrow interval bandwidth, which can help to ensure the economic and secure operation of the electric power system.
ArticleNumber 123497
Author Tang, Jingwei
Deng, Yuwen
Hu, Jianming
Luo, Qingxi
Heng, Jiani
Author_xml – sequence: 1
  givenname: Jianming
  surname: Hu
  fullname: Hu, Jianming
  organization: College of Economics and Statistics, Guangzhou University, Guangzhou, China
– sequence: 2
  givenname: Qingxi
  surname: Luo
  fullname: Luo, Qingxi
  email: 2111964058@e.gzhu.edu.cn
  organization: College of Economics and Statistics, Guangzhou University, Guangzhou, China
– sequence: 3
  givenname: Jingwei
  surname: Tang
  fullname: Tang, Jingwei
  organization: Department of Mathematics, Faculty of Science and Technology, University of Macau, Macau, China
– sequence: 4
  givenname: Jiani
  surname: Heng
  fullname: Heng, Jiani
  organization: Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, 100190, China
– sequence: 5
  givenname: Yuwen
  surname: Deng
  fullname: Deng, Yuwen
  organization: College of Economics and Statistics, Guangzhou University, Guangzhou, China
BookMark eNp9kF9LwzAUxYNMcE6_gQ8Fn1uTtE3TF0GG_2Dgiz6HLL0ZqV3SJdnG_PRm1GefLvdwzoHzu0Yz6ywgdEdwQTBhD30BFvzmVFBMaUFoWbXNBZoT3pQ5a3g9Q3NcMpzXVUWv0HUIPca45m07R7B0Vju_lYP5gS6LsB2dl0OmnD24YR-Ns-nb7aWNZoDMw8ZDCEnNLMSj898hS_HsaGyXje4IPjM2gj-kUNJByRCN3dygSy2HALd_d4G-Xp4_l2_56uP1ffm0ylXJ65jrmiimSVcyStZsLTlQzTpK2qaSsupKrda81kTXmkKru7ZSALIBXqsmeXVZLtD91Dt6t9tDiKJ3e58WBEEZq3DTtJgnVzW5lHcheNBi9GYr_UkQLM5ARS8moOIMVExAU-xxikFacDDgRVAGrILOpKFRdM78X_ALwwGGpg
CitedBy_id crossref_primary_10_1109_TSTE_2024_3389023
crossref_primary_10_1145_3637552
crossref_primary_10_1016_j_energy_2023_129079
crossref_primary_10_1016_j_energy_2023_130155
crossref_primary_10_1016_j_apenergy_2022_120279
crossref_primary_10_1016_j_energy_2024_130305
crossref_primary_10_3390_en15249299
crossref_primary_10_1016_j_seja_2024_100059
crossref_primary_10_1016_j_resourpol_2023_103563
crossref_primary_10_1007_s10489_022_03958_7
crossref_primary_10_1016_j_apenergy_2023_122341
crossref_primary_10_1088_1361_6501_ad2e68
crossref_primary_10_3389_fenrg_2023_1211360
crossref_primary_10_1016_j_energy_2022_125276
crossref_primary_10_1016_j_apenergy_2023_122248
crossref_primary_10_1016_j_asoc_2024_111649
crossref_primary_10_3389_fenrg_2022_1097048
crossref_primary_10_1016_j_apenergy_2024_122900
crossref_primary_10_3390_en16041988
crossref_primary_10_1016_j_energy_2023_126608
crossref_primary_10_1016_j_energy_2023_129639
Cites_doi 10.1016/j.eswa.2017.12.041
10.1016/j.ijepes.2019.105556
10.1063/5.0007003
10.3390/electronics8080876
10.1016/j.epsr.2020.106865
10.1109/TITS.2011.2106209
10.1016/j.renene.2021.07.113
10.1016/j.apenergy.2021.116842
10.1016/j.renene.2020.03.098
10.1016/j.jhydrol.2014.08.026
10.1016/j.energy.2020.117081
10.1016/j.ins.2020.10.034
10.3390/en11123336
10.1016/j.renene.2019.01.006
10.1016/j.renene.2020.08.077
10.1111/rssb.12021
10.1016/j.neucom.2019.07.058
10.7465/jkdi.2020.31.6.1155
10.1109/TSTE.2017.2774195
10.1016/j.csda.2019.106876
10.1109/TPWRS.2013.2287871
10.1016/j.renene.2018.05.031
10.1016/j.enconman.2019.02.028
10.1016/j.asoc.2019.105550
10.1109/TNNLS.2019.2946414
10.1016/j.asoc.2020.106327
10.1016/j.cnsns.2020.105617
10.1080/01621459.2017.1307116
10.1080/01621459.2012.751873
ContentType Journal Article
Copyright 2022 Elsevier Ltd
Copyright Elsevier BV Jun 1, 2022
Copyright_xml – notice: 2022 Elsevier Ltd
– notice: Copyright Elsevier BV Jun 1, 2022
DBID AAYXX
CITATION
7SP
7ST
7TB
8FD
C1K
F28
FR3
KR7
L7M
SOI
DOI 10.1016/j.energy.2022.123497
DatabaseName CrossRef
Electronics & Communications Abstracts
Environment Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Environmental Sciences and Pollution Management
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Environment Abstracts
DatabaseTitle CrossRef
Civil Engineering Abstracts
Technology Research Database
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
Engineering Research Database
Environment Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
Environmental Sciences and Pollution Management
DatabaseTitleList
Civil Engineering Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Economics
Environmental Sciences
EISSN 1873-6785
ExternalDocumentID 10_1016_j_energy_2022_123497
S0360544222004005
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1RT
1~.
1~5
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAHCO
AAIAV
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AARJD
AAXUO
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACIWK
ACRLP
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFKWA
AFRAH
AFTJW
AGHFR
AGUBO
AGYEJ
AHIDL
AIEXJ
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BELTK
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
JARJE
KOM
LY6
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RIG
RNS
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SSR
SSZ
T5K
TN5
XPP
ZMT
~02
~G-
29G
6TJ
AAHBH
AAQXK
AAXKI
AAYXX
ABFNM
ABXDB
ADMUD
AFJKZ
AHHHB
ASPBG
AVWKF
AZFZN
CITATION
EJD
FEDTE
FGOYB
G-2
G8K
HVGLF
HZ~
R2-
SAC
SEW
WUQ
7SP
7ST
7TB
8FD
C1K
F28
FR3
KR7
L7M
SOI
ID FETCH-LOGICAL-c385t-f51c6f1d3621b6ba8e2f6d21974aa4d3fcb85f1f5f2e9fd94ceea7e85c7a8ef33
IEDL.DBID AIKHN
ISSN 0360-5442
IngestDate Thu Oct 10 16:00:22 EDT 2024
Thu Sep 26 17:02:31 EDT 2024
Sat Apr 27 15:44:44 EDT 2024
IsPeerReviewed true
IsScholarly true
Keywords Temporal convolutional network
Conformalized quantile regression
Wind power interval prediction
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c385t-f51c6f1d3621b6ba8e2f6d21974aa4d3fcb85f1f5f2e9fd94ceea7e85c7a8ef33
PQID 2664077908
PQPubID 2045484
ParticipantIDs proquest_journals_2664077908
crossref_primary_10_1016_j_energy_2022_123497
elsevier_sciencedirect_doi_10_1016_j_energy_2022_123497
PublicationCentury 2000
PublicationDate 2022-06-01
2022-06-00
20220601
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-06-01
  day: 01
PublicationDecade 2020
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Energy (Oxford)
PublicationYear 2022
Publisher Elsevier Ltd
Elsevier BV
Publisher_xml – name: Elsevier Ltd
– name: Elsevier BV
References Naik, Bisoi, Dash (bib4) 2018; 129
Johansson (bib16) 2018; 97
Gan (bib34) 2021; 191
Papadopoulos, Gammerman, Vovk (bib17) 2008
Shi, Liang, Venkata (bib23) 2017; 9
Khosravi (bib7) 2011; 12
Shahih, Purwarianti (bib31) 2019
Qi (bib39) 2017; 8
Wan (bib33) 2019; 8
Zhao, Jia (bib30) 2020; 12
Meinshausen (bib38) 2006; 7
Lei, Wasserman (bib13) 2014
Hu, Heng, Wen (bib40) 2020; 162
Pearce, Zaki, Brintrup, Neely (bib6) 2018
Yu, Zhang, Zang (bib37) 2018; 11
Wan (bib9) 2013; 29
He, Zhang, Ren (bib35) 2016
Nix, Weigend (bib8) 1994; vol. 1
Kumar (bib32) 2021
Lei (bib15) 2018; 523
Wang (bib27) 2019; 31
Hu, Lin, Tang, Zhao (bib41) 2020; 92
Ding (bib25) 2019; 365
Wang, Wang, Li (bib1) 2021; 179
Ma (bib22) 2021; vol. 22
Niu, Yu, Tang, Wu, Reformat (bib5) 2020; 196
Wang, Jv (bib10) 2021; 95
Li (bib26) 2020; 155
Shim (bib42) 2020; 31
Lei, Robins, Wasserman (bib36) 2013; 108
Ye (bib11) 2014; 519
Papadopoulos (bib18) 2008
Tian, Song (bib19) 2020; 144
Zhou, Wang, Guo (bib28) 2021; 550
Jiang, Huang, Yang, Yan, Zhang (bib12) 2019; 185
Romano, Patterson, Candes (bib20) 2019; 32
Li (bib21) 2020; 116
Yuan, Chen, Jiang, Yuan (bib24) 2019; 82
Vovk, Gammerman, Glenn Shafer (bib14) 2005
Romero (bib29) 2021
D. Wei, J. Wang, X. Niu, Z. Li, Wind speed forecasting system based on gated recurrent units and convolutional spiking neural networks, Appl Energy 292(2021), 116842.
Naik, Dash, Dhar (bib3) 2019; 136
Naik (10.1016/j.energy.2022.123497_bib3) 2019; 136
Lei (10.1016/j.energy.2022.123497_bib15) 2018; 523
10.1016/j.energy.2022.123497_bib2
Lei (10.1016/j.energy.2022.123497_bib13) 2014
Vovk (10.1016/j.energy.2022.123497_bib14) 2005
Tian (10.1016/j.energy.2022.123497_bib19) 2020; 144
Yuan (10.1016/j.energy.2022.123497_bib24) 2019; 82
Romano (10.1016/j.energy.2022.123497_bib20) 2019; 32
Shi (10.1016/j.energy.2022.123497_bib23) 2017; 9
Pearce (10.1016/j.energy.2022.123497_bib6) 2018
Wan (10.1016/j.energy.2022.123497_bib33) 2019; 8
Jiang (10.1016/j.energy.2022.123497_bib12) 2019; 185
Zhao (10.1016/j.energy.2022.123497_bib30) 2020; 12
Papadopoulos (10.1016/j.energy.2022.123497_bib17) 2008
Khosravi (10.1016/j.energy.2022.123497_bib7) 2011; 12
Shahih (10.1016/j.energy.2022.123497_bib31) 2019
Wang (10.1016/j.energy.2022.123497_bib10) 2021; 95
Wang (10.1016/j.energy.2022.123497_bib27) 2019; 31
Meinshausen (10.1016/j.energy.2022.123497_bib38) 2006; 7
Wan (10.1016/j.energy.2022.123497_bib9) 2013; 29
Johansson (10.1016/j.energy.2022.123497_bib16) 2018; 97
Naik (10.1016/j.energy.2022.123497_bib4) 2018; 129
Zhou (10.1016/j.energy.2022.123497_bib28) 2021; 550
Wang (10.1016/j.energy.2022.123497_bib1) 2021; 179
Lei (10.1016/j.energy.2022.123497_bib36) 2013; 108
He (10.1016/j.energy.2022.123497_bib35) 2016
Papadopoulos (10.1016/j.energy.2022.123497_bib18) 2008
Hu (10.1016/j.energy.2022.123497_bib41) 2020; 92
Niu (10.1016/j.energy.2022.123497_bib5) 2020; 196
Yu (10.1016/j.energy.2022.123497_bib37) 2018; 11
Nix (10.1016/j.energy.2022.123497_bib8) 1994; vol. 1
Kumar (10.1016/j.energy.2022.123497_bib32) 2021
Hu (10.1016/j.energy.2022.123497_bib40) 2020; 162
Li (10.1016/j.energy.2022.123497_bib26) 2020; 155
Gan (10.1016/j.energy.2022.123497_bib34) 2021; 191
Li (10.1016/j.energy.2022.123497_bib21) 2020; 116
Ding (10.1016/j.energy.2022.123497_bib25) 2019; 365
Ye (10.1016/j.energy.2022.123497_bib11) 2014; 519
Ma (10.1016/j.energy.2022.123497_bib22) 2021; vol. 22
Qi (10.1016/j.energy.2022.123497_bib39) 2017; 8
Shim (10.1016/j.energy.2022.123497_bib42) 2020; 31
Romero (10.1016/j.energy.2022.123497_bib29) 2021
References_xml – volume: 8
  start-page: 876
  year: 2019
  ident: bib33
  article-title: Multivariate temporal convolutional network: a deep neural networks approach for multivariate time series forecasting
  publication-title: Electronics
  contributor:
    fullname: Wan
– volume: 162
  start-page: 1208
  year: 2020
  end-page: 1226
  ident: bib40
  article-title: Deterministic and probabilistic wind speed forecasting with de-noising-reconstruction strategy and quantile regression based algorithm
  publication-title: Renew Energy
  contributor:
    fullname: Wen
– year: 2019
  ident: bib31
  article-title: Combining word and character vector representation on neural machine translation
  publication-title: 2019 Fourth International conference on Informatics and computing (ICIC)
  contributor:
    fullname: Purwarianti
– volume: 8
  year: 2017
  ident: bib39
  article-title: Quantile regression models and their applications: a review
  publication-title: J Biometrics Biostat
  contributor:
    fullname: Qi
– volume: 185
  start-page: 758
  year: 2019
  end-page: 773
  ident: bib12
  article-title: A novel probabilistic wind speed prediction approach using real time refined variational model decomposition and conditional kernel density estimation
  publication-title: Energy Convers Manag
  contributor:
    fullname: Zhang
– volume: 32
  year: 2019
  ident: bib20
  article-title: Conformalized quantile regression
  publication-title: Adv Neural Inf Process Syst
  contributor:
    fullname: Candes
– volume: 365
  start-page: 54
  year: 2019
  end-page: 61
  ident: bib25
  article-title: A gated recurrent unit neural networks based wind speed error correction model for short-term wind power forecasting
  publication-title: Neurocomputing
  contributor:
    fullname: Ding
– volume: 116
  start-page: 105556
  year: 2020
  ident: bib21
  article-title: Dynamic dependence modelling of wind power uncertainty considering heteroscedastic effect
  publication-title: Int J Electr Power Energy Syst
  contributor:
    fullname: Li
– volume: 155
  start-page: 197
  year: 2020
  end-page: 211
  ident: bib26
  article-title: The short-term interval prediction of wind power using the deep learning model with gradient descend optimization
  publication-title: Renew Energy
  contributor:
    fullname: Li
– start-page: 6473
  year: 2018
  end-page: 6482
  ident: bib6
  article-title: High-quality prediction intervals for deep learning: a distribution-free, ensembled approach
  publication-title: 35th Int. Conf. Mach. Learn. ICML 2018
  contributor:
    fullname: Neely
– volume: 523
  start-page: 1094
  year: 2018
  end-page: 1111
  ident: bib15
  article-title: Distribution-free predictive inference for regression
  publication-title: J Am Stat Assoc
  contributor:
    fullname: Lei
– volume: 97
  start-page: 394
  year: 2018
  end-page: 404
  ident: bib16
  article-title: Interpretable regression trees using conformal prediction
  publication-title: Expert Syst Appl
  contributor:
    fullname: Johansson
– start-page: 64
  year: 2008
  end-page: 69
  ident: bib17
  article-title: Normalized nonconformity measures for regression conformal prediction
  publication-title: International conference on artificial intelligence and applications
  contributor:
    fullname: Vovk
– volume: 31
  start-page: 1155
  year: 2020
  end-page: 1165
  ident: bib42
  article-title: Noncrossing varying coefficient support vector quantile regression
  publication-title: Journal of the Korean Data and Information Science Society
  contributor:
    fullname: Shim
– volume: 92
  start-page: 106327
  year: 2020
  ident: bib41
  article-title: A new wind power interval prediction approach based on reservoir computing and a quality-driven loss function
  publication-title: Appl Soft Comput
  contributor:
    fullname: Zhao
– start-page: 71
  year: 2014
  end-page: 96
  ident: bib13
  article-title: Distribution-free prediction bands for non-parametric regression
  publication-title: J Roy Stat Soc B Stat Methodol
  contributor:
    fullname: Wasserman
– volume: 9
  start-page: 1177
  year: 2017
  end-page: 1187
  ident: bib23
  article-title: Direct interval forecast of uncertain wind power based on recurrent neural networks
  publication-title: IEEE Trans Sustain Energy
  contributor:
    fullname: Venkata
– volume: 12
  start-page: 537
  year: 2011
  end-page: 547
  ident: bib7
  article-title: Prediction intervals to account for uncertainties in travel time prediction
  publication-title: IEEE Trans Intell Transport Syst
  contributor:
    fullname: Khosravi
– volume: 82
  start-page: 105550
  year: 2019
  ident: bib24
  article-title: Prediction interval of wind power using parameter optimized beta distribution based LSTM model
  publication-title: Appl Soft Comput
  contributor:
    fullname: Yuan
– volume: 191
  start-page: 106865
  year: 2021
  ident: bib34
  article-title: Temporal convolutional networks interval prediction model for wind speed forecasting
  publication-title: Elec Power Syst Res
  contributor:
    fullname: Gan
– volume: 31
  start-page: 3814
  year: 2019
  end-page: 3827
  ident: bib27
  article-title: Deep learning method based on gated recurrent unit and variational mode decomposition for short-term wind power interval prediction
  publication-title: IEEE Transact Neural Networks Learn Syst
  contributor:
    fullname: Wang
– volume: 11
  start-page: 3336
  year: 2018
  ident: bib37
  article-title: Wind power interval forecasting based on confidence interval optimization
  publication-title: Energies
  contributor:
    fullname: Zang
– volume: 7
  start-page: 983
  year: 2006
  end-page: 999
  ident: bib38
  article-title: Quantile regression forests
  publication-title: J Mach Learn Res
  contributor:
    fullname: Meinshausen
– year: 2008
  ident: bib18
  article-title: Inductive conformal prediction: theory and application to neural networks
  publication-title: Tools in artificial intelligence
  contributor:
    fullname: Papadopoulos
– volume: 144
  year: 2020
  ident: bib19
  article-title: Bayesian bridge-randomized penalized quantile regression
  publication-title: Comput Stat Data Anal
  contributor:
    fullname: Song
– volume: vol. 1
  year: 1994
  ident: bib8
  article-title: Estimating the mean and variance of the target probability distribution
  publication-title: Proceedings of 1994 ieee international conference on neural networks (ICNN'94)
  contributor:
    fullname: Weigend
– volume: 136
  start-page: 701
  year: 2019
  end-page: 731
  ident: bib3
  article-title: A multi-objective wind speed and wind power prediction interval forecasting using variational modes decomposition based Multi-kernel robust ridge regression
  publication-title: Renew Energy
  contributor:
    fullname: Dhar
– volume: 196
  start-page: 117081
  year: 2020
  ident: bib5
  article-title: Wind power forecasting using attention-based gated recurrent unit network
  publication-title: Energy
  contributor:
    fullname: Reformat
– year: 2021
  ident: bib29
  article-title: CKConv: Continuous kernel convolution for sequential data
  contributor:
    fullname: Romero
– volume: 12
  year: 2020
  ident: bib30
  article-title: A short-term hybrid wind power prediction model based on singular spectrum analysis and temporal convolutional networks
  publication-title: J Renew Sustain Energy
  contributor:
    fullname: Jia
– year: 2016
  ident: bib35
  article-title: Deep residual learning for image recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
  contributor:
    fullname: Ren
– volume: 129
  start-page: 357
  year: 2018
  end-page: 383
  ident: bib4
  article-title: Prediction interval forecasting of wind speed and wind power using modes decomposition based low rank multi-kernel ridge regression
  publication-title: Renew Energy
  contributor:
    fullname: Dash
– volume: 179
  year: 2021
  ident: bib1
  article-title: Wind speed deterministic forecasting and probabilistic interval forecasting approach based on deep learning, modified tunicate swarm algorithm, and quantile regression
  publication-title: Renew Energy
  contributor:
    fullname: Li
– volume: 95
  start-page: 105617
  year: 2021
  ident: bib10
  article-title: A novel grey prediction model based on quantile regression
  publication-title: Commun Nonlinear Sci Numer Simulat
  contributor:
    fullname: Jv
– volume: 108
  start-page: 278
  year: 2013
  end-page: 287
  ident: bib36
  article-title: Distribution-free prediction sets
  publication-title: J Am Stat Assoc
  contributor:
    fullname: Wasserman
– volume: 519
  start-page: 925
  year: 2014
  end-page: 933
  ident: bib11
  article-title: Multi-objective optimization for construction of prediction interval of hydrological models based on ensemble simulations
  publication-title: J Hydrol
  contributor:
    fullname: Ye
– volume: vol. 22
  start-page: 101410
  year: 2021
  ident: bib22
  article-title: Modeling of lead removal by living Scenedesmus obliquus using backpropagation (BP) neural network algorithm
  contributor:
    fullname: Ma
– year: 2021
  ident: bib32
  article-title: Role of convolutional neural networks for any real time image classification, recognition and analysis
  publication-title: Mater Today Proc
  contributor:
    fullname: Kumar
– volume: 29
  start-page: 1033
  year: 2013
  end-page: 1044
  ident: bib9
  article-title: Probabilistic forecasting of wind power generation using extreme learning machine
  publication-title: IEEE Trans Power Syst
  contributor:
    fullname: Wan
– volume: 550
  start-page: 207
  year: 2021
  end-page: 220
  ident: bib28
  article-title: Multi-objective prediction intervals for wind power forecast based on deep neural networks
  publication-title: Inf Sci
  contributor:
    fullname: Guo
– year: 2005
  ident: bib14
  article-title: Algorithmic learning in a random world
  contributor:
    fullname: Glenn Shafer
– volume: 97
  start-page: 394
  issue: 2018
  year: 2018
  ident: 10.1016/j.energy.2022.123497_bib16
  article-title: Interpretable regression trees using conformal prediction
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2017.12.041
  contributor:
    fullname: Johansson
– volume: 116
  start-page: 105556
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib21
  article-title: Dynamic dependence modelling of wind power uncertainty considering heteroscedastic effect
  publication-title: Int J Electr Power Energy Syst
  doi: 10.1016/j.ijepes.2019.105556
  contributor:
    fullname: Li
– volume: 12
  issue: 5
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib30
  article-title: A short-term hybrid wind power prediction model based on singular spectrum analysis and temporal convolutional networks
  publication-title: J Renew Sustain Energy
  doi: 10.1063/5.0007003
  contributor:
    fullname: Zhao
– start-page: 6473
  year: 2018
  ident: 10.1016/j.energy.2022.123497_bib6
  article-title: High-quality prediction intervals for deep learning: a distribution-free, ensembled approach
  contributor:
    fullname: Pearce
– volume: 8
  start-page: 876
  issue: 8
  year: 2019
  ident: 10.1016/j.energy.2022.123497_bib33
  article-title: Multivariate temporal convolutional network: a deep neural networks approach for multivariate time series forecasting
  publication-title: Electronics
  doi: 10.3390/electronics8080876
  contributor:
    fullname: Wan
– volume: 191
  start-page: 106865
  year: 2021
  ident: 10.1016/j.energy.2022.123497_bib34
  article-title: Temporal convolutional networks interval prediction model for wind speed forecasting
  publication-title: Elec Power Syst Res
  doi: 10.1016/j.epsr.2020.106865
  contributor:
    fullname: Gan
– year: 2008
  ident: 10.1016/j.energy.2022.123497_bib18
  article-title: Inductive conformal prediction: theory and application to neural networks
  contributor:
    fullname: Papadopoulos
– year: 2021
  ident: 10.1016/j.energy.2022.123497_bib29
  contributor:
    fullname: Romero
– volume: 12
  start-page: 537
  issue: 2
  year: 2011
  ident: 10.1016/j.energy.2022.123497_bib7
  article-title: Prediction intervals to account for uncertainties in travel time prediction
  publication-title: IEEE Trans Intell Transport Syst
  doi: 10.1109/TITS.2011.2106209
  contributor:
    fullname: Khosravi
– volume: 179
  year: 2021
  ident: 10.1016/j.energy.2022.123497_bib1
  article-title: Wind speed deterministic forecasting and probabilistic interval forecasting approach based on deep learning, modified tunicate swarm algorithm, and quantile regression
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2021.07.113
  contributor:
    fullname: Wang
– volume: vol. 22
  start-page: 101410
  year: 2021
  ident: 10.1016/j.energy.2022.123497_bib22
  contributor:
    fullname: Ma
– start-page: 64
  year: 2008
  ident: 10.1016/j.energy.2022.123497_bib17
  article-title: Normalized nonconformity measures for regression conformal prediction
  contributor:
    fullname: Papadopoulos
– ident: 10.1016/j.energy.2022.123497_bib2
  doi: 10.1016/j.apenergy.2021.116842
– volume: 155
  start-page: 197
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib26
  article-title: The short-term interval prediction of wind power using the deep learning model with gradient descend optimization
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2020.03.098
  contributor:
    fullname: Li
– volume: 519
  start-page: 925
  year: 2014
  ident: 10.1016/j.energy.2022.123497_bib11
  article-title: Multi-objective optimization for construction of prediction interval of hydrological models based on ensemble simulations
  publication-title: J Hydrol
  doi: 10.1016/j.jhydrol.2014.08.026
  contributor:
    fullname: Ye
– volume: 32
  year: 2019
  ident: 10.1016/j.energy.2022.123497_bib20
  article-title: Conformalized quantile regression
  publication-title: Adv Neural Inf Process Syst
  contributor:
    fullname: Romano
– volume: 7
  start-page: 983
  year: 2006
  ident: 10.1016/j.energy.2022.123497_bib38
  article-title: Quantile regression forests
  publication-title: J Mach Learn Res
  contributor:
    fullname: Meinshausen
– year: 2005
  ident: 10.1016/j.energy.2022.123497_bib14
  contributor:
    fullname: Vovk
– volume: 196
  start-page: 117081
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib5
  article-title: Wind power forecasting using attention-based gated recurrent unit network
  publication-title: Energy
  doi: 10.1016/j.energy.2020.117081
  contributor:
    fullname: Niu
– volume: 550
  start-page: 207
  year: 2021
  ident: 10.1016/j.energy.2022.123497_bib28
  article-title: Multi-objective prediction intervals for wind power forecast based on deep neural networks
  publication-title: Inf Sci
  doi: 10.1016/j.ins.2020.10.034
  contributor:
    fullname: Zhou
– volume: 11
  start-page: 3336
  issue: 12
  year: 2018
  ident: 10.1016/j.energy.2022.123497_bib37
  article-title: Wind power interval forecasting based on confidence interval optimization
  publication-title: Energies
  doi: 10.3390/en11123336
  contributor:
    fullname: Yu
– volume: 8
  issue: 3
  year: 2017
  ident: 10.1016/j.energy.2022.123497_bib39
  article-title: Quantile regression models and their applications: a review
  publication-title: J Biometrics Biostat
  contributor:
    fullname: Qi
– volume: 136
  start-page: 701
  year: 2019
  ident: 10.1016/j.energy.2022.123497_bib3
  article-title: A multi-objective wind speed and wind power prediction interval forecasting using variational modes decomposition based Multi-kernel robust ridge regression
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2019.01.006
  contributor:
    fullname: Naik
– volume: 162
  start-page: 1208
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib40
  article-title: Deterministic and probabilistic wind speed forecasting with de-noising-reconstruction strategy and quantile regression based algorithm
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2020.08.077
  contributor:
    fullname: Hu
– start-page: 71
  year: 2014
  ident: 10.1016/j.energy.2022.123497_bib13
  article-title: Distribution-free prediction bands for non-parametric regression
  publication-title: J Roy Stat Soc B Stat Methodol
  doi: 10.1111/rssb.12021
  contributor:
    fullname: Lei
– volume: 365
  start-page: 54
  year: 2019
  ident: 10.1016/j.energy.2022.123497_bib25
  article-title: A gated recurrent unit neural networks based wind speed error correction model for short-term wind power forecasting
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.07.058
  contributor:
    fullname: Ding
– year: 2019
  ident: 10.1016/j.energy.2022.123497_bib31
  article-title: Combining word and character vector representation on neural machine translation
  contributor:
    fullname: Shahih
– volume: 31
  start-page: 1155
  issue: 6
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib42
  article-title: Noncrossing varying coefficient support vector quantile regression
  publication-title: Journal of the Korean Data and Information Science Society
  doi: 10.7465/jkdi.2020.31.6.1155
  contributor:
    fullname: Shim
– volume: 9
  start-page: 1177
  issue: 3
  year: 2017
  ident: 10.1016/j.energy.2022.123497_bib23
  article-title: Direct interval forecast of uncertain wind power based on recurrent neural networks
  publication-title: IEEE Trans Sustain Energy
  doi: 10.1109/TSTE.2017.2774195
  contributor:
    fullname: Shi
– volume: 144
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib19
  article-title: Bayesian bridge-randomized penalized quantile regression
  publication-title: Comput Stat Data Anal
  doi: 10.1016/j.csda.2019.106876
  contributor:
    fullname: Tian
– volume: 29
  start-page: 1033
  issue: 3
  year: 2013
  ident: 10.1016/j.energy.2022.123497_bib9
  article-title: Probabilistic forecasting of wind power generation using extreme learning machine
  publication-title: IEEE Trans Power Syst
  doi: 10.1109/TPWRS.2013.2287871
  contributor:
    fullname: Wan
– year: 2016
  ident: 10.1016/j.energy.2022.123497_bib35
  article-title: Deep residual learning for image recognition
  contributor:
    fullname: He
– volume: 129
  start-page: 357
  year: 2018
  ident: 10.1016/j.energy.2022.123497_bib4
  article-title: Prediction interval forecasting of wind speed and wind power using modes decomposition based low rank multi-kernel ridge regression
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2018.05.031
  contributor:
    fullname: Naik
– volume: 185
  start-page: 758
  year: 2019
  ident: 10.1016/j.energy.2022.123497_bib12
  article-title: A novel probabilistic wind speed prediction approach using real time refined variational model decomposition and conditional kernel density estimation
  publication-title: Energy Convers Manag
  doi: 10.1016/j.enconman.2019.02.028
  contributor:
    fullname: Jiang
– volume: 82
  start-page: 105550
  year: 2019
  ident: 10.1016/j.energy.2022.123497_bib24
  article-title: Prediction interval of wind power using parameter optimized beta distribution based LSTM model
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2019.105550
  contributor:
    fullname: Yuan
– volume: 31
  start-page: 3814
  issue: 10
  year: 2019
  ident: 10.1016/j.energy.2022.123497_bib27
  article-title: Deep learning method based on gated recurrent unit and variational mode decomposition for short-term wind power interval prediction
  publication-title: IEEE Transact Neural Networks Learn Syst
  doi: 10.1109/TNNLS.2019.2946414
  contributor:
    fullname: Wang
– volume: 92
  start-page: 106327
  year: 2020
  ident: 10.1016/j.energy.2022.123497_bib41
  article-title: A new wind power interval prediction approach based on reservoir computing and a quality-driven loss function
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2020.106327
  contributor:
    fullname: Hu
– volume: 95
  start-page: 105617
  year: 2021
  ident: 10.1016/j.energy.2022.123497_bib10
  article-title: A novel grey prediction model based on quantile regression
  publication-title: Commun Nonlinear Sci Numer Simulat
  doi: 10.1016/j.cnsns.2020.105617
  contributor:
    fullname: Wang
– volume: 523
  start-page: 1094
  year: 2018
  ident: 10.1016/j.energy.2022.123497_bib15
  article-title: Distribution-free predictive inference for regression
  publication-title: J Am Stat Assoc
  doi: 10.1080/01621459.2017.1307116
  contributor:
    fullname: Lei
– year: 2021
  ident: 10.1016/j.energy.2022.123497_bib32
  article-title: Role of convolutional neural networks for any real time image classification, recognition and analysis
  publication-title: Mater Today Proc
  contributor:
    fullname: Kumar
– volume: 108
  start-page: 278
  issue: 501
  year: 2013
  ident: 10.1016/j.energy.2022.123497_bib36
  article-title: Distribution-free prediction sets
  publication-title: J Am Stat Assoc
  doi: 10.1080/01621459.2012.751873
  contributor:
    fullname: Lei
– volume: vol. 1
  year: 1994
  ident: 10.1016/j.energy.2022.123497_bib8
  article-title: Estimating the mean and variance of the target probability distribution
  contributor:
    fullname: Nix
SSID ssj0005899
Score 2.5411687
Snippet Wind power interval prediction is an effective technique for quantifying forecasting uncertainty caused by the intermittent and fluctuant characteristics of...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Publisher
StartPage 123497
SubjectTerms Algorithms
Conformalized quantile regression
Decision making
Electric power
Electric power systems
Forecasting
Iterative methods
Mathematical models
Predictions
Regression
Renewable energy
Temporal convolutional network
Wind power
Wind power interval prediction
Title Conformalized temporal convolutional quantile regression networks for wind power interval forecasting
URI https://dx.doi.org/10.1016/j.energy.2022.123497
https://www.proquest.com/docview/2664077908
Volume 248
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS8MwED_28aAvolPxY0oefI2zS9I2j2NsTAd78AN9C2mbyGTUuU4EH_zbvbQpogiCTyUlV8rd5XeX9ncXgDNhBcYpaSjmyozyWHMqw8BSi87DDe4gfLfPWTi541cP4qEBw7oWxtEqPfZXmF6itb_T89rsLefz3g1iL-Yb7hNG6YmiCW33kwh3YO3B5XQy-2J6xOUxkm4-dQJ1BV1J8zJliR1uFPv9c0Rx7ro__R6hfmB1GYDG27DlM0cyqF5uBxom78BGXVhcdGB_9FW0hhP9qi12wbiyPpebLubvJiO-G9WCOMa59zwcvbyikhEjyMo8VuTYnOQVSbwgKE7ecPtOlu5UNTIvmZIohPdNqgvHnd6Du_Hodjih_ngFmrJYrKkVQRraIMMQFiRhomPTt2GGCBZxrXnGbJrEwgZW2L6RNpMc46mOTCzSCOdaxvahlT_n5gCIsIhVLOTyQjJudSozyTTnLBVasEyzQ6C1StWy6qKhanrZk6pMoJwJVGWCQ4hqvatv3qAQ6P-Q7NZmUn41FgqTEPS6SF7ER_9-8DFsulHFEutCa716NSeYj6yTU2iefwSn3uvcdXp9P_0EtVTkCQ
link.rule.ids 315,786,790,4516,24137,27946,27947,45609,45703
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDLZgHMYF8ZoYDMiBa7Z1SdrmiKZN43kBpN2irE3Q0FTGugmJA78dp03FQ0hIHJs6VWU7n53oswNwJqzAOCUNxVyZUR5rTmUYWGrRebjBHYTv9nkbjh745ViM16Bf1cI4WqXH_hLTC7T2Ix2vzc58Ou3cIfZivuGOMApPFOuwgdlA17l2-_0LzyMuLpF00tSJV_VzBcnLFAV2uE3s9dqI4dz1fvo9Pv1A6iL8DLdhy-eN5Lz8tR1YM9ku1Kuy4nwXGoPPkjUU9Gs23wPjivpcZjqbvpmU-F5UM-L45t7v8OllhSpGhCAL81hSYzOSlRTxnOB08oqbdzJ3d6qRacGTxEk4bhKdO-b0PjwMB_f9EfWXK9CExWJJrQiS0AYpBrBgEk50bHo2TBG_Iq41T5lNJrGwgRW2Z6RNJcdoqiMTiyRCWctYA2rZc2YOgAiLSMVCLruScasTmUqmOWeJ0IKlmjWBVipV87KHhqrIZU-qNIFyJlClCZoQVXpX33xBIcz_MbNVmUn5tZgrTEHQ5yLZjQ___eFTqI_ub67V9cXt1RFsujclX6wFteViZY4xM1lOTgrP-wCf9eM5
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=Conformalized+temporal+convolutional+quantile+regression+networks+for+wind+power+interval+forecasting&rft.jtitle=Energy+%28Oxford%29&rft.au=Hu%2C+Jianming&rft.au=Luo%2C+Qingxi&rft.au=Tang%2C+Jingwei&rft.au=Heng%2C+Jiani&rft.date=2022-06-01&rft.issn=0360-5442&rft.volume=248&rft.spage=123497&rft_id=info:doi/10.1016%2Fj.energy.2022.123497&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_energy_2022_123497
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-5442&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-5442&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-5442&client=summon