Conditional Variational Autoencoder Informed Probabilistic Wind Power Curve Modeling

In this paper, a conditional variational autoencoder based method is proposed for the probabilistic wind power curve modeling task. To advance the modeling performance, the latent random variable is introduced to characterize underlying weather and wind turbine conditions. The infinite Gaussian mixt...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on sustainable energy Ročník 14; číslo 4; s. 1 - 15
Hlavní autori: Zheng, Zhong, Yang, Luoxiao, Zhang, Zijun
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.10.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:1949-3029, 1949-3037
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In this paper, a conditional variational autoencoder based method is proposed for the probabilistic wind power curve modeling task. To advance the modeling performance, the latent random variable is introduced to characterize underlying weather and wind turbine conditions. The infinite Gaussian mixture model is adopted to better model the asymmetric and heterogeneous conditional distribution of the wind power given the wind speed. The conditional variational autoencoder is composed of an encoder and a decoder network. The encoder infers the state of the latent random variable given the wind speed and wind power, while the decoder learns the observational conditional distribution of the wind power given the wind speed and latent variable. With a well-trained conditional variational autoencoder, the conditional probability density function of the wind power could be estimated through the decoder network by sampling the latent random variable from its prior distribution. Wind turbine supervisory control and data acquisition datasets are used in experiments to validate advantages of the proposed method. Experimental results show that the proposed method outperforms other benchmarking deterministic and probabilistic wind power curve models with the lower continuous ranked probability score and more reliable and sharper prediction intervals. Experiments also reflect the better robustness of the conditional variational autoencoder to data pre-processed using univariate or multivariate inputs, as well as its superiority and potential for the wind power estimation considering multivariate inputs.
AbstractList In this paper, a conditional variational autoencoder based method is proposed for the probabilistic wind power curve modeling task. To advance the modeling performance, the latent random variable is introduced to characterize underlying weather and wind turbine conditions. The infinite Gaussian mixture model is adopted to better model the asymmetric and heterogeneous conditional distribution of the wind power given the wind speed. The conditional variational autoencoder is composed of an encoder and a decoder network. The encoder infers the state of the latent random variable given the wind speed and wind power, while the decoder learns the observational conditional distribution of the wind power given the wind speed and latent variable. With a well-trained conditional variational autoencoder, the conditional probability density function of the wind power could be estimated through the decoder network by sampling the latent random variable from its prior distribution. Wind turbine supervisory control and data acquisition datasets are used in experiments to validate advantages of the proposed method. Experimental results show that the proposed method outperforms other benchmarking deterministic and probabilistic wind power curve models with the lower continuous ranked probability score and more reliable and sharper prediction intervals. Experiments also reflect the better robustness of the conditional variational autoencoder to data pre-processed using univariate or multivariate inputs, as well as its superiority and potential for the wind power estimation considering multivariate inputs.
In this article, a conditional variational autoencoder based method is proposed for the probabilistic wind power curve modeling task. To advance the modeling performance, the latent random variable is introduced to characterize underlying weather and wind turbine conditions. The infinite Gaussian mixture model is adopted to better model the asymmetric and heterogeneous conditional distribution of the wind power given the wind speed. The conditional variational autoencoder is composed of an encoder and a decoder network. The encoder infers the state of the latent random variable given the wind speed and wind power, while the decoder learns the observational conditional distribution of the wind power given the wind speed and latent variable. With a well-trained conditional variational autoencoder, the conditional probability density function of the wind power could be estimated through the decoder network by sampling the latent random variable from its prior distribution. Wind turbine supervisory control and data acquisition datasets are used in experiments to validate advantages of the proposed method. Experimental results show that the proposed method outperforms other benchmarking deterministic and probabilistic wind power curve models with the lower continuous ranked probability score and more reliable and sharper prediction intervals. Experiments also reflect the better robustness of the conditional variational autoencoder to data pre-processed using univariate or multivariate inputs, as well as its superiority and potential for the wind power estimation considering multivariate inputs.
Author Zhang, Zijun
Yang, Luoxiao
Zheng, Zhong
Author_xml – sequence: 1
  givenname: Zhong
  orcidid: 0000-0002-1741-0554
  surname: Zheng
  fullname: Zheng, Zhong
  organization: School of Data Science, City University of Hong Kong, Kowloon, Hong Kong
– sequence: 2
  givenname: Luoxiao
  orcidid: 0000-0001-6298-5333
  surname: Yang
  fullname: Yang, Luoxiao
  organization: School of Data Science, City University of Hong Kong, Kowloon, Hong Kong
– sequence: 3
  givenname: Zijun
  orcidid: 0000-0002-2717-5033
  surname: Zhang
  fullname: Zhang, Zijun
  organization: School of Data Science, City University of Hong Kong, Kowloon, Hong Kong
BookMark eNp9kE9Lw0AQxRepYK39AIKHgOfU_Z_kWELVQkXBqMdlszuRLWm2bhLFb29qi4gH5zLD8H7DvHeKRo1vAKFzgmeE4OyqeCwWM4opmzGaMkHEERqTjGcxwywZ_cw0O0HTtl3joRhjkuExKnLfWNc53-g6etbB6cM87zsPjfEWQrRsKh82YKOH4Etdutq1nTPRi2uGlf8YFHkf3iG6G9S1a17P0HGl6xamhz5BT9eLIr-NV_c3y3y-ig3NeBfLqsK45BJKIBYLKwBYYiS2QCHFxpqyEowDCI45MSA05aXFQBNZWkNBsgm63N_dBv_WQ9upte_D8H2raColT4UcfE5QsleZ4Ns2QKWM675tdkG7WhGsdimqXYpql6I6pDiQ5A-5DW6jw-e_zMWecQDwS0-4SDFhX-wlgOE
CODEN ITSEAJ
CitedBy_id crossref_primary_10_1109_TSTE_2024_3458916
crossref_primary_10_1016_j_apenergy_2024_122785
crossref_primary_10_1016_j_apenergy_2024_124356
crossref_primary_10_1016_j_rser_2025_115605
crossref_primary_10_1051_e3sconf_202454003007
crossref_primary_10_3390_en18102461
crossref_primary_10_1016_j_energy_2024_133628
crossref_primary_10_1016_j_oceaneng_2025_121507
crossref_primary_10_1016_j_enconman_2025_119680
crossref_primary_10_1109_JIOT_2025_3526150
crossref_primary_10_3390_en18051275
Cites_doi 10.1016/j.renene.2019.09.145
10.1016/j.neucom.2018.01.077
10.1016/j.egyr.2020.06.018
10.1080/01621459.2011.643745
10.1080/02664763.2010.545119
10.1109/TSTE.2013.2247641
10.1016/j.rser.2014.01.033
10.1002/we.509
10.1016/j.neucom.2013.08.020
10.1016/j.rser.2013.10.030
10.1088/1742-6596/524/1/012108
10.1109/EEM.2017.7981885
10.1109/TSTE.2014.2345059
10.1198/016214506000001437
10.1109/ICRERA.2016.7884500
10.1109/ISET-India.2011.6145371
10.1109/TSTE.2019.2920386
10.1023/B:STCO.0000035301.49549.88
10.1016/j.renene.2008.10.022
10.1016/j.jclepro.2022.131793
10.1016/j.renene.2018.02.081
10.1016/j.rser.2016.01.114
10.1080/01621459.2014.977385
10.1109/TPWRS.2010.2045774
10.1016/j.rser.2019.109422
10.1109/TSTE.2018.2820198
10.1016/j.engappai.2016.08.003
10.1109/TNN.2010.2096824
10.1016/j.apenergy.2021.116913
10.1007/s11222-007-9038-7
10.1016/j.renene.2019.08.060
10.1016/j.enconman.2019.02.028
10.1109/TSTE.2018.2866543
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
7ST
7TB
8FD
C1K
FR3
H8D
KR7
L7M
SOI
DOI 10.1109/TSTE.2023.3283515
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
Environment Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Environmental Sciences and Pollution Management
Engineering Research Database
Aerospace Database
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Environment Abstracts
DatabaseTitle CrossRef
Aerospace Database
Civil Engineering Abstracts
Technology Research Database
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
Engineering Research Database
Environment Abstracts
Advanced Technologies Database with Aerospace
Environmental Sciences and Pollution Management
DatabaseTitleList
Aerospace Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1949-3037
EndPage 15
ExternalDocumentID 10_1109_TSTE_2023_3283515
10145801
Genre orig-research
GroupedDBID 0R~
4.4
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
AENEX
AFRAH
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
P2P
RIA
RIE
RNS
5VS
AAYXX
AGSQL
CITATION
EJD
7SP
7ST
7TB
8FD
C1K
FR3
H8D
KR7
L7M
SOI
ID FETCH-LOGICAL-c294t-6ff00b46ebe1d05d5ee37c60de2e80cdcbf534ee54041ce5a24bd0e276bdc2e63
IEDL.DBID RIE
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001072574400036&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1949-3029
IngestDate Mon Jun 30 09:37:52 EDT 2025
Sat Nov 29 03:13:24 EST 2025
Tue Nov 18 22:04:51 EST 2025
Wed Aug 27 02:57:13 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
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-c294t-6ff00b46ebe1d05d5ee37c60de2e80cdcbf534ee54041ce5a24bd0e276bdc2e63
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-2717-5033
0000-0002-1741-0554
0000-0001-6298-5333
PQID 2866485633
PQPubID 2040348
PageCount 15
ParticipantIDs proquest_journals_2866485633
crossref_citationtrail_10_1109_TSTE_2023_3283515
crossref_primary_10_1109_TSTE_2023_3283515
ieee_primary_10145801
PublicationCentury 2000
PublicationDate 2023-10-01
PublicationDateYYYYMMDD 2023-10-01
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-10-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE transactions on sustainable energy
PublicationTitleAbbrev TSTE
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
ref34
ref15
ref37
ref14
ref36
ref11
ref33
ref32
ref1
ref39
ref16
ref38
ref19
vapnik (ref10) 1999
chung (ref29) 0; 28
uria (ref17) 2016; 17
ref23
ref25
ref20
ref42
ref41
ref22
sohn (ref30) 0; 28
ref21
ref28
(ref24) 1998
ref27
kingma (ref31) 0
dudley (ref2) 2019
kingma (ref18) 2014
ref8
ref7
zambom (ref26) 2013; 5
ref9
ref4
ref3
ref6
ref5
ref40
References_xml – year: 2019
  ident: ref2
  article-title: BP statistical review of world energy 2016
– ident: ref13
  doi: 10.1016/j.renene.2019.09.145
– volume: 28
  start-page: 2980
  year: 0
  ident: ref29
  article-title: A recurrent latent variable model for sequential data
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref41
  doi: 10.1016/j.neucom.2018.01.077
– ident: ref22
  doi: 10.1016/j.egyr.2020.06.018
– ident: ref14
  doi: 10.1080/01621459.2011.643745
– ident: ref34
  doi: 10.1080/02664763.2010.545119
– ident: ref23
  doi: 10.1109/TSTE.2013.2247641
– ident: ref39
  doi: 10.1016/j.rser.2014.01.033
– volume: 28
  start-page: 3483
  year: 0
  ident: ref30
  article-title: Learning structured output representation using deep conditional generative models
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref19
  doi: 10.1002/we.509
– ident: ref38
  doi: 10.1016/j.neucom.2013.08.020
– ident: ref11
  doi: 10.1016/j.rser.2013.10.030
– ident: ref32
  doi: 10.1088/1742-6596/524/1/012108
– ident: ref12
  doi: 10.1109/EEM.2017.7981885
– ident: ref5
  doi: 10.1109/TSTE.2014.2345059
– ident: ref35
  doi: 10.1198/016214506000001437
– ident: ref28
  doi: 10.1109/ICRERA.2016.7884500
– ident: ref9
  doi: 10.1109/ISET-India.2011.6145371
– volume: 5
  start-page: 20
  year: 2013
  ident: ref26
  article-title: A review of kernel density estimation with applications to econometrics
  publication-title: Int Econ Rev
– start-page: 3581
  year: 2014
  ident: ref18
  article-title: Semi-supervised learning with deep generative models
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref15
  doi: 10.1109/TSTE.2019.2920386
– ident: ref25
  doi: 10.1023/B:STCO.0000035301.49549.88
– ident: ref8
  doi: 10.1016/j.renene.2008.10.022
– ident: ref42
  doi: 10.1016/j.jclepro.2022.131793
– ident: ref27
  doi: 10.1016/j.renene.2018.02.081
– ident: ref1
  doi: 10.1016/j.rser.2016.01.114
– ident: ref20
  doi: 10.1080/01621459.2014.977385
– ident: ref37
  doi: 10.1109/TPWRS.2010.2045774
– ident: ref6
  doi: 10.1016/j.rser.2019.109422
– year: 1999
  ident: ref10
  publication-title: The Nature of Statistical Learning Theory
– ident: ref16
  doi: 10.1109/TSTE.2018.2820198
– ident: ref21
  doi: 10.1016/j.engappai.2016.08.003
– ident: ref36
  doi: 10.1109/TNN.2010.2096824
– ident: ref3
  doi: 10.1016/j.apenergy.2021.116913
– start-page: 1
  year: 0
  ident: ref31
  article-title: Auto-encoding variational bayes
  publication-title: Proc Int Conf Learn Representations
– ident: ref33
  doi: 10.1007/s11222-007-9038-7
– ident: ref4
  doi: 10.1016/j.renene.2019.08.060
– volume: 17
  start-page: 7184
  year: 2016
  ident: ref17
  article-title: Neural autoregressive distribution estimation
  publication-title: J Mach Learn Res
– year: 1998
  ident: ref24
  publication-title: International Electrotechnical Commission Wind Turbine Generator Systems-Part 12 Wind Turbine Power Performance Testing
– ident: ref40
  doi: 10.1016/j.enconman.2019.02.028
– ident: ref7
  doi: 10.1109/TSTE.2018.2866543
SSID ssj0000333630
Score 2.4286246
Snippet In this paper, a conditional variational autoencoder based method is proposed for the probabilistic wind power curve modeling task. To advance the modeling...
In this article, a conditional variational autoencoder based method is proposed for the probabilistic wind power curve modeling task. To advance the modeling...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Coders
Computational modeling
Conditional probability
Data acquisition
Data models
Data processing
Data-driven models
deep neural networks
Electric power distribution
Modelling
Multivariate analysis
Predictive models
Probabilistic logic
probabilistic modeling
Probabilistic models
Probability density functions
Probability theory
Random variables
Statistical analysis
Supervisory control and data acquisition
Turbines
Wind power
wind power curve
Wind power generation
Wind speed
Wind turbines
Title Conditional Variational Autoencoder Informed Probabilistic Wind Power Curve Modeling
URI https://ieeexplore.ieee.org/document/10145801
https://www.proquest.com/docview/2866485633
Volume 14
WOSCitedRecordID wos001072574400036&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: 1949-3037
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000333630
  issn: 1949-3029
  databaseCode: RIE
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46POjBnxOnU3LwJHRLmzRtj2NseJAxsM7dSpu8giCrdO3-fvPSbgxEwVsPSSl5SV--9-P7CHm0JOKacQeyLHWEVL4TpQa4-iozzgzSPLMl_4uXYDYLl8to3jar214YALDFZzDAR5vL14WqMVQ2tLqyIXZrHQaBbJq1dgEVxjmXVlvE4HLM53tRm8V0WTSMX-PJAKXCBxwZxlAFd88PWWGVH39j62KmZ__8uHNy2t4l6agx_gU5gNUlOdljGLwi8bjAnLSN99GFwcVt7I-O6qpADksNJW1akkDTeWlON1bLInkzfTdwnc5RRY2O63IDFHXTsHu9S96mk3j87LRCCo7yIlE5Ms8Zy4Q0BnM187UPwAMlmQYPQqa0ynKfCwBzexOuAj_1RKYZeIHMtPJA8mvSWRUruCGUBV5uEBDXTGiRhyzlIRLmK26gjZ8yt0fYdlkT1bKMo9jFZ2LRBosStESClkhaS_TI027KV0Ox8dfgLi793sBm1XukvzVe0p7CdeKFUorQl5zf_jLtjhzj25vqvD7pVGUN9-RIbaqPdflgN9g3BjjNSA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFA4yBfXB68Tp1Dz4JHTLmjRrH8dwTJxjYJ17K21yCoJs0l1-vzlpNgai4FsfElpykp585_J9hNxbEnHNuAdZlnpCqsCLUgNcA5UZZwZpntmS__GgPRyGk0k0cs3qthcGAGzxGTTw0eby9UwtMVTWtLqyIXZr7aJ0lmvX2oRUGOdcWnURg8wxo-9HLo_ZYlEzfo0fGygW3uDIMYY6uFueyEqr_PgfWyfTO_7n552QI3ebpJ3S_KdkB6Zn5HCLY_CcxN0ZZqVtxI-ODTJ20T_aWS5myGKpoaBlUxJoOirM-cZ6WaRvpu8GsNMR6qjR7rJYAUXlNOxfr5K33mPc7XtOSsFTfiQWnsxzxjIhjclamgU6AOBtJZkGH0KmtMrygAsAc38TLQVB6otMM_DbMtPKB8kvSGU6m8Iloazt5wYDcc2EFnnIUh4iZb7iBtwEKWvVCFsva6IczzjKXXwmFm-wKEFLJGiJxFmiRh42U75Kko2_Bldx6bcGlqteI_W18RJ3DueJH0opwkByfvXLtDuy349fBsngafh8TQ7wTWWtXp1UFsUSbsieWi0-5sWt3Wzf42DQkQ
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=Conditional+Variational+Autoencoder+Informed+Probabilistic+Wind+Power+Curve+Modeling&rft.jtitle=IEEE+transactions+on+sustainable+energy&rft.au=Zheng%2C+Zhong&rft.au=Yang%2C+Luoxiao&rft.au=Zhang%2C+Zijun&rft.date=2023-10-01&rft.issn=1949-3029&rft.eissn=1949-3037&rft.volume=14&rft.issue=4&rft.spage=2445&rft.epage=2460&rft_id=info:doi/10.1109%2FTSTE.2023.3283515&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSTE_2023_3283515
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1949-3029&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1949-3029&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1949-3029&client=summon