Short-term multi-step wind power prediction model based on Pt-Transformer neural network integrating spatio-temporal feature and sparse attention

•A wind power forecasting method based on the time series Transformer model is proposed.•Novel model improves noisy data handling, time-series dependency capture, and efficiency.•Introduce a multi-step autoregressive prediction framework using Teacher forcing. The accuracy and stability of wind powe...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Electric power systems research Ročník 248; s. 111970
Hlavní autoři: Zhang, Zhiyan, Sun, Zhenyang, Guo, Xianghui, Guo, Ruipeng, Yang, Xiaoliang, Yang, Pengju
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.11.2025
Témata:
ISSN:0378-7796
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract •A wind power forecasting method based on the time series Transformer model is proposed.•Novel model improves noisy data handling, time-series dependency capture, and efficiency.•Introduce a multi-step autoregressive prediction framework using Teacher forcing. The accuracy and stability of wind power prediction are crucial for grid dispatching. However, precise wind power prediction faces three major challenges: effective mitigating data noise, representing complex spatio-temporal features, and selecting an appropriate prediction model. To address these challenges, this paper proposes a new wind power prediction model called process temporal transformer (Pt-Transformer). Firstly, an exponential weighted moving average (EWMA) method is employed to filter the noise of original wind characteristics while maintaining data complexity. Secondly, a seasonal trend decomposition (STD) model combined with a temporal autoencoder (TAE) is implemented to efficiently extract complex spatio-temporal characteristics. Furthermore, a sparse attention mechanism combined with the Transformer architecture is introduced to effectively extract high-dimensional latent space representations. Finally, two case studies are conducted using data from a cluster of wind farms and a single wind farm in central China, and three models, namely Transformer, Prob-Transformer, and Pt-Transformer, are used for prediction. The results show that the Pt-Transformer model outperforms the other two models in prediction accuracy and stability, reflecting its excellent performance in short-term multi-step wind power generation prediction.
AbstractList •A wind power forecasting method based on the time series Transformer model is proposed.•Novel model improves noisy data handling, time-series dependency capture, and efficiency.•Introduce a multi-step autoregressive prediction framework using Teacher forcing. The accuracy and stability of wind power prediction are crucial for grid dispatching. However, precise wind power prediction faces three major challenges: effective mitigating data noise, representing complex spatio-temporal features, and selecting an appropriate prediction model. To address these challenges, this paper proposes a new wind power prediction model called process temporal transformer (Pt-Transformer). Firstly, an exponential weighted moving average (EWMA) method is employed to filter the noise of original wind characteristics while maintaining data complexity. Secondly, a seasonal trend decomposition (STD) model combined with a temporal autoencoder (TAE) is implemented to efficiently extract complex spatio-temporal characteristics. Furthermore, a sparse attention mechanism combined with the Transformer architecture is introduced to effectively extract high-dimensional latent space representations. Finally, two case studies are conducted using data from a cluster of wind farms and a single wind farm in central China, and three models, namely Transformer, Prob-Transformer, and Pt-Transformer, are used for prediction. The results show that the Pt-Transformer model outperforms the other two models in prediction accuracy and stability, reflecting its excellent performance in short-term multi-step wind power generation prediction.
ArticleNumber 111970
Author Guo, Xianghui
Guo, Ruipeng
Yang, Pengju
Yang, Xiaoliang
Sun, Zhenyang
Zhang, Zhiyan
Author_xml – sequence: 1
  givenname: Zhiyan
  surname: Zhang
  fullname: Zhang, Zhiyan
  email: 2004074@zzuli.edu.cn
  organization: School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
– sequence: 2
  givenname: Zhenyang
  surname: Sun
  fullname: Sun, Zhenyang
  email: 2020994906@qq.com
  organization: School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
– sequence: 3
  givenname: Xianghui
  surname: Guo
  fullname: Guo, Xianghui
  email: 1781330452@qq.com
  organization: School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
– sequence: 4
  givenname: Ruipeng
  surname: Guo
  fullname: Guo, Ruipeng
  organization: School of Mechanical and Electrical Engineering, Henan Vocational College of Applied Technology, Zhengzhou, Henan Province 450042, China
– sequence: 5
  givenname: Xiaoliang
  orcidid: 0000-0003-4579-322X
  surname: Yang
  fullname: Yang, Xiaoliang
  email: yangxl@hnu.edu.cn
  organization: School of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
– sequence: 6
  givenname: Pengju
  surname: Yang
  fullname: Yang, Pengju
  email: 569197581@qq.com
  organization: Senior Engineer Jinshan Power Supply Company, State Grid Shanghai Municipal Electric Power Company, Shanghai 200540, China
BookMark eNp9kMtOAyEUhlnUxFZ9AVe8wFRgLrSJG9N4S5poYl0ThjlTqTMwOVAbH8M3lklduejqh3A-fvhmZOK8A0KuOZtzxqub3RyGgHPBRDnnnC8lm5Apy-Uik3JZnZNZCDvGWLWU5ZT8vH14jFkE7Gm_76LNQoSBHqxr6OAPgHRAaKyJ1jva-wY6WusADU3b15htULvQeuzToIM96i5FPHj8pNZF2KKO1m1pGFL61NIPfpxpQcc9AtWpJZ1hSMsYwY0tl-Ss1V2Aq7-8IO8P95vVU7Z-eXxe3a0zkzMRs7oqZWnyUpoFr4WUi6LIcymk0WLZVqwGKLTUuqjavGxECcCkYMB10wpTs4bnF2RxvNegDwGhVcbG8Zkuorad4kyNOtVOjTrVqFMddSZU_EMHtL3G79PQ7RGC9KkvC6iCseBMsotgomq8PYX_AmSZl7I
CitedBy_id crossref_primary_10_1016_j_epsr_2025_112176
Cites_doi 10.35833/MPCE.2021.000717
10.1049/cit2.12076
10.3390/en17112568
10.1016/j.apenergy.2019.04.188
10.1016/j.apenergy.2022.120601
10.1080/15435075.2023.2244589
10.1016/j.epsr.2022.107776
10.1016/j.energy.2023.128730
10.1016/j.renene.2014.11.084
10.3390/su151813424
10.1109/JSEN.2023.3273279
10.1016/j.renene.2024.122055
10.1016/j.patcog.2024.110552
10.1016/j.energy.2022.123990
10.1016/j.jclepro.2019.118447
10.1155/2023/4950487
10.1016/j.energy.2023.130225
10.3390/jmse12060925
10.1016/j.energy.2022.125231
10.3390/en15228417
10.1109/TITS.2023.3337150
10.1007/s00202-024-02440-6
10.1016/j.ijforecast.2015.03.001
10.1109/TSTE.2019.2912270
10.3390/sym15040951
10.1016/j.asoc.2019.03.035
10.3390/pr11113247
10.1016/j.energy.2024.131546
10.1109/ACCESS.2022.3151975
10.1016/j.energy.2024.133511
10.1016/j.renene.2019.01.031
10.1016/j.apenergy.2022.118801
10.3390/e25040647
10.1016/j.renene.2021.12.100
10.1016/j.energy.2020.118980
10.1007/s12530-019-09271-y
10.1007/s40565-015-0151-x
ContentType Journal Article
Copyright 2025 Elsevier B.V.
Copyright_xml – notice: 2025 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.epsr.2025.111970
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_epsr_2025_111970
S0378779625005619
GroupedDBID --K
--M
-~X
.~1
0R~
1B1
1~.
1~5
29G
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9DU
9JN
AABNK
AAEDT
AAEDW
AAHCO
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARJD
AATTM
AAXKI
AAXUO
AAYWO
ABFNM
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFS
ACIWK
ACLOT
ACNNM
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADHUB
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHIDL
AHJVU
AI.
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BELTK
BJAXD
BKOJK
BLXMC
CS3
DU5
E.L
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HVGLF
HZ~
IHE
J1W
JARJE
JJJVA
K-O
KOM
LY6
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
ROL
RPZ
SAC
SDF
SDG
SES
SET
SEW
SPC
SPCBC
SSR
SST
SSW
SSZ
T5K
VH1
WUQ
ZMT
~G-
~HD
AAYXX
CITATION
ID FETCH-LOGICAL-c302t-b6575c357c81b27784433727ca29f60bee4a7aa46f35d25ee0720e1adf2cb0d13
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001521583400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0378-7796
IngestDate Tue Nov 18 22:25:28 EST 2025
Thu Nov 27 01:03:50 EST 2025
Sat Nov 29 17:15:14 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Seasonal trend decomposition
Sparse attention mechanism
Wind power prediction
Transformer
Temporal autoencoder
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c302t-b6575c357c81b27784433727ca29f60bee4a7aa46f35d25ee0720e1adf2cb0d13
ORCID 0000-0003-4579-322X
ParticipantIDs crossref_citationtrail_10_1016_j_epsr_2025_111970
crossref_primary_10_1016_j_epsr_2025_111970
elsevier_sciencedirect_doi_10_1016_j_epsr_2025_111970
PublicationCentury 2000
PublicationDate November 2025
2025-11-00
PublicationDateYYYYMMDD 2025-11-01
PublicationDate_xml – month: 11
  year: 2025
  text: November 2025
PublicationDecade 2020
PublicationTitle Electric power systems research
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Ma, Yang, Lin (bib0009) 2020; 11
Liu, Fu (bib0033) 2023; 284
Dong, Ma, Zhang, Yang (bib0038) 2022; 10
Wang, Sun, Zhang, Srinivasan (bib0013) 2025; 319
Sireesha, Thotakura (bib0018) 2024; 106
Nouhitehrani, Caro, Juan (bib0028) 2024; 66
Iversen, Morales, Møller, Madsen (bib0025) 2016; 32
Yuzgec, Dokur, Balci (bib0007) 2024; 300
Wang, Xu, Song, Zhang, Li, Zhou, Zhang (bib0015) 2023; 333
Niu, Yu, Sun, Gao, Wang (bib0026) 2022; 313
Wu, Luo, Yang, Guo, Li, Xue (bib0006) 2022; 7
Mulewa, Parmar, De (bib0024) 2024; 21
Zhu, Han, Chai, Zhao (bib0032) 2023; 15
Aasim, Singh, Mohapatra (bib0027) 2019; 136
Liu, He, Liu, Chen, Dong (bib0041) 2024; 25
Ding, Ye, Guo (bib0003) 2023; 2023
Xiong, Lou, Meng, Wang, Ma, Wang (bib0030) 2022; 206
Li, Wang, Shan, Li (bib0001) 2022; 15
Zhang, Lin, Liu (bib0016) 2022; 185
Cheng, Luo, Jin (bib0037) 2024; 312
Duan, Wang, Ma, Tian, Fang, Cheng, Chang, Liu (bib0004) 2021; 214
Liu, Chen (bib0014) 2019; 249
Kanagarathinam, Aruna, Ravivarman, Safran, Alfarhood, Alrajhi (bib0020) 2023; 15
Yu, Ma, Ma (bib0035) 2024; 153
Du, Wang, Yang, Niu (bib0005) 2019; 80
Tian, Wang, Zhou, Wang, Zhao, Ni (bib0034) 2023; 25
Mir, Shafieezadeh, Heidari, Ghadimi (bib0012) 2020; 11
Ban, Chen, Xiong, Zhuo, Huang (bib0031) 2024; 290
Wan, Gong, Wei, Al-Bukhaiti, Ji, Ma, Yao (bib0023) 2024; 12
Yang, Pang, Xiang, Li, Gu (bib0022) 2023; 11
Wang, Xu, Yin, Pan, Wu, Han (bib0008) 2024; 43
Icer, Rahman, Adhikari (bib0039) 2024
Bashir, Wang, Tahir, Zhang (bib0019) 2025; 239
Wu, Wang, Zeng (bib0002) 2022; 252
Zhang, Deng, Wang, Li, Zhao, Yang (bib0021) 2024; 17
He, Liu, Wu, Wang (bib0029) 2023; 23
Li, Zhao, Tseng, Tan (bib0011) 2020; 242
Chen, Hong, Zhou (bib0036) 2022; 10
Mu, Yang, Wang, Yan, Qi (bib0017) 2016; 4
Shukur, Lee (bib0010) 2015; 76
Wu, Meng, Fan, Zhang, Liu (bib0040) 2022; 261
Chen (10.1016/j.epsr.2025.111970_bib0036) 2022; 10
Wang (10.1016/j.epsr.2025.111970_bib0015) 2023; 333
Wu (10.1016/j.epsr.2025.111970_bib0006) 2022; 7
Wang (10.1016/j.epsr.2025.111970_bib0013) 2025; 319
Xiong (10.1016/j.epsr.2025.111970_bib0030) 2022; 206
Sireesha (10.1016/j.epsr.2025.111970_bib0018) 2024; 106
Du (10.1016/j.epsr.2025.111970_bib0005) 2019; 80
Niu (10.1016/j.epsr.2025.111970_bib0026) 2022; 313
Dong (10.1016/j.epsr.2025.111970_bib0038) 2022; 10
Kanagarathinam (10.1016/j.epsr.2025.111970_bib0020) 2023; 15
Zhu (10.1016/j.epsr.2025.111970_bib0032) 2023; 15
Icer (10.1016/j.epsr.2025.111970_bib0039) 2024
Bashir (10.1016/j.epsr.2025.111970_bib0019) 2025; 239
Tian (10.1016/j.epsr.2025.111970_bib0034) 2023; 25
Li (10.1016/j.epsr.2025.111970_bib0011) 2020; 242
Duan (10.1016/j.epsr.2025.111970_bib0004) 2021; 214
Nouhitehrani (10.1016/j.epsr.2025.111970_bib0028) 2024; 66
Ma (10.1016/j.epsr.2025.111970_bib0009) 2020; 11
Liu (10.1016/j.epsr.2025.111970_bib0014) 2019; 249
Yang (10.1016/j.epsr.2025.111970_bib0022) 2023; 11
Wu (10.1016/j.epsr.2025.111970_bib0002) 2022; 252
He (10.1016/j.epsr.2025.111970_bib0029) 2023; 23
Liu (10.1016/j.epsr.2025.111970_bib0041) 2024; 25
Iversen (10.1016/j.epsr.2025.111970_bib0025) 2016; 32
Yu (10.1016/j.epsr.2025.111970_bib0035) 2024; 153
Yuzgec (10.1016/j.epsr.2025.111970_bib0007) 2024; 300
Aasim (10.1016/j.epsr.2025.111970_bib0027) 2019; 136
Ban (10.1016/j.epsr.2025.111970_bib0031) 2024; 290
Wang (10.1016/j.epsr.2025.111970_bib0008) 2024; 43
Zhang (10.1016/j.epsr.2025.111970_bib0021) 2024; 17
Mulewa (10.1016/j.epsr.2025.111970_bib0024) 2024; 21
Shukur (10.1016/j.epsr.2025.111970_bib0010) 2015; 76
Mir (10.1016/j.epsr.2025.111970_bib0012) 2020; 11
Wu (10.1016/j.epsr.2025.111970_bib0040) 2022; 261
Wan (10.1016/j.epsr.2025.111970_bib0023) 2024; 12
Zhang (10.1016/j.epsr.2025.111970_bib0016) 2022; 185
Ding (10.1016/j.epsr.2025.111970_bib0003) 2023; 2023
Li (10.1016/j.epsr.2025.111970_bib0001) 2022; 15
Cheng (10.1016/j.epsr.2025.111970_bib0037) 2024; 312
Liu (10.1016/j.epsr.2025.111970_bib0033) 2023; 284
Mu (10.1016/j.epsr.2025.111970_bib0017) 2016; 4
References_xml – volume: 23
  start-page: 13360
  year: 2023
  end-page: 13376
  ident: bib0029
  article-title: Condition monitoring and fault detection of wind turbine driveline with the implementation of deep residual long short-term memory network
  publication-title: IEEE Sens. J.
– volume: 21
  start-page: 1238
  year: 2024
  end-page: 1252
  ident: bib0024
  article-title: Attention based Transformer coupled with convoluted neural network for ultra-short- and short-term forecasting of multiple wind farms
  publication-title: Int. J. Green Energy
– volume: 312
  year: 2024
  ident: bib0037
  article-title: Integrating domain knowledge into transformer for short-term wind power forecasting
  publication-title: Energy
– volume: 11
  start-page: 906
  year: 2020
  end-page: 915
  ident: bib0009
  article-title: Ultra-short-term probabilistic wind turbine power forecast based on empirical dynamic modeling
  publication-title: IEEE Trans. Sustain. Energy
– volume: 25
  start-page: 4947
  year: 2024
  end-page: 4963
  ident: bib0041
  article-title: WindTrans: transformer-based wind speed forecasting method for high-speed railway
  publication-title: IEEE Trans. Intell. Transp. Syst.
– volume: 261
  year: 2022
  ident: bib0040
  article-title: Multistep short-term wind speed forecasting using transformer
  publication-title: Energy
– volume: 15
  start-page: 951
  year: 2023
  ident: bib0032
  article-title: Time series analysis based on informer algorithms: a survey
  publication-title: Symmetry
– volume: 10
  start-page: 19621
  year: 2022
  end-page: 19628
  ident: bib0036
  article-title: Transformer network for remaining useful life prediction of lithium-ion batteries
  publication-title: IEEE Access
– volume: 242
  year: 2020
  ident: bib0011
  article-title: Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm
  publication-title: J. Clean. Prod.
– volume: 15
  start-page: 8417
  year: 2022
  ident: bib0001
  article-title: Research on multi-step prediction of short-term wind power based on combination model and error correction
  publication-title: Energies
– volume: 43
  start-page: 224
  year: 2024
  end-page: 232
  ident: bib0008
  article-title: Wind power prediction method based on spatial correlation andStacking ensemble learning
  publication-title: Electr. Power Eng. Technol.
– volume: 333
  year: 2023
  ident: bib0015
  article-title: A convolutional Transformer-based truncated Gaussian density network with data denoising for wind speed forecasting
  publication-title: Appl. Energy
– volume: 185
  start-page: 611
  year: 2022
  end-page: 628
  ident: bib0016
  article-title: Short-term offshore wind power forecasting - A hybrid model based on Discrete Wavelet Transform (DWT), Seasonal Autoregressive Integrated Moving Average (SARIMA), and deep-learning-based Long Short-Term Memory (LSTM)
  publication-title: Renew. Energy
– volume: 153
  year: 2024
  ident: bib0035
  article-title: Robformer: a robust decomposition transformer for long-term time series forecasting
  publication-title: Pattern. Recognit.
– volume: 319
  year: 2025
  ident: bib0013
  article-title: Optimization of deterministic and probabilistic forecasting for wind power based on ensemble learning
  publication-title: Energy
– volume: 17
  start-page: 2568
  year: 2024
  ident: bib0021
  article-title: Wind power prediction based on EMD-KPCA-BiLSTM-ATT model
  publication-title: Energies
– volume: 290
  year: 2024
  ident: bib0031
  article-title: The univariate model for long-term wind speed forecasting based on wavelet soft threshold denoising and improved Autoformer
  publication-title: Energy
– volume: 10
  start-page: 1184
  year: 2022
  end-page: 1193
  ident: bib0038
  article-title: Wind power prediction based on multi-class autoregressive moving average model with logistic function
  publication-title: J. Mod. Power Syst. Clean Energy
– volume: 249
  start-page: 392
  year: 2019
  end-page: 408
  ident: bib0014
  article-title: Data processing strategies in wind energy forecasting models and applications: a comprehensive review
  publication-title: Appl. Energy
– start-page: 372
  year: 2024
  end-page: 378
  ident: bib0039
  article-title: Autoregressive modeling of time series in renewable energy systems
  publication-title: 2024 IEEE 15th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)
– volume: 7
  start-page: 129
  year: 2022
  end-page: 143
  ident: bib0006
  article-title: A comprehensive review on deep learning approaches in wind forecasting applications
  publication-title: CAAI Trans. Intell. Technol.
– volume: 300
  year: 2024
  ident: bib0007
  article-title: A novel hybrid model based on empirical mode decomposition and echo state network for wind power forecasting
  publication-title: Energy
– volume: 76
  start-page: 637
  year: 2015
  end-page: 647
  ident: bib0010
  article-title: Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA
  publication-title: Renew. Energy
– volume: 11
  start-page: 559
  year: 2020
  end-page: 573
  ident: bib0012
  article-title: Application of hybrid forecast engine based intelligent algorithm and feature selection for wind signal prediction
  publication-title: Evol. Syst.
– volume: 12
  start-page: 925
  year: 2024
  ident: bib0023
  article-title: Multistep forecasting method for offshore wind turbine power based on multi-timescale input and improved transformer
  publication-title: J. Mar. Sci. Eng.
– volume: 313
  year: 2022
  ident: bib0026
  article-title: Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism
  publication-title: Appl. Energy
– volume: 4
  start-page: 265
  year: 2016
  end-page: 274
  ident: bib0017
  article-title: Spatial dispersion of wind speeds and its influence on the forecasting error of wind power in a wind farm
  publication-title: J. Mod. Power Syst. Clean Energy
– volume: 214
  year: 2021
  ident: bib0004
  article-title: Short-term wind power forecasting using the hybrid model of improved variational mode decomposition and Correntropy long Short -term memory neural network
  publication-title: Energy
– volume: 106
  start-page: 7643
  year: 2024
  end-page: 7666
  ident: bib0018
  article-title: Wind power prediction using optimized MLP-NN machine learning forecasting model
  publication-title: Electr. Eng.
– volume: 25
  start-page: 647
  year: 2023
  ident: bib0034
  article-title: An adaptive hybrid model for wind power prediction based on the IVMD-FE-Ad-Informer
  publication-title: Entropy
– volume: 239
  year: 2025
  ident: bib0019
  article-title: Wind and solar power forecasting based on hybrid CNN-ABiLSTM, CNN-transformer-MLP models
  publication-title: Renew. Energy
– volume: 284
  year: 2023
  ident: bib0033
  article-title: Renewable energy forecasting: a self-supervised learning-based transformer variant
  publication-title: Energy
– volume: 2023
  year: 2023
  ident: bib0003
  article-title: A multistep direct and indirect strategy for predicting wind direction based on the EMD-LSTM model
  publication-title: Struct. Control Health Monit.
– volume: 136
  start-page: 758
  year: 2019
  end-page: 768
  ident: bib0027
  article-title: Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting
  publication-title: Renew. Energy
– volume: 66
  year: 2024
  ident: bib0028
  article-title: Computation of prediction intervals of wind energy based on the EWMA and BOA techniques
  publication-title: Sustain. Energy Technol. Assess.
– volume: 80
  start-page: 93
  year: 2019
  end-page: 106
  ident: bib0005
  article-title: A novel hybrid model for short-term wind power forecasting
  publication-title: Appl. Soft. Comput.
– volume: 11
  start-page: 3247
  year: 2023
  ident: bib0022
  article-title: A novel hybrid deep learning model for forecasting Ultra-short-term time series wind speeds for wind turbines
  publication-title: Processes
– volume: 206
  year: 2022
  ident: bib0030
  article-title: Short-term wind power forecasting based on attention mechanism and Deep learning
  publication-title: Electr. Power Syst. Res.
– volume: 252
  year: 2022
  ident: bib0002
  article-title: Interpretable wind speed prediction with multivariate time series and temporal fusion transformers
  publication-title: Energy
– volume: 15
  year: 2023
  ident: bib0020
  article-title: Enhancing sustainable urban energy management through short-term wind power forecasting using LSTM Neural network
  publication-title: Sustainability
– volume: 32
  start-page: 981
  year: 2016
  end-page: 990
  ident: bib0025
  article-title: Short-term probabilistic forecasting of wind speed using stochastic differential equations
  publication-title: Int. J. Forecast.
– volume: 10
  start-page: 1184
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0038
  article-title: Wind power prediction based on multi-class autoregressive moving average model with logistic function
  publication-title: J. Mod. Power Syst. Clean Energy
  doi: 10.35833/MPCE.2021.000717
– volume: 7
  start-page: 129
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0006
  article-title: A comprehensive review on deep learning approaches in wind forecasting applications
  publication-title: CAAI Trans. Intell. Technol.
  doi: 10.1049/cit2.12076
– volume: 17
  start-page: 2568
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0021
  article-title: Wind power prediction based on EMD-KPCA-BiLSTM-ATT model
  publication-title: Energies
  doi: 10.3390/en17112568
– volume: 249
  start-page: 392
  year: 2019
  ident: 10.1016/j.epsr.2025.111970_bib0014
  article-title: Data processing strategies in wind energy forecasting models and applications: a comprehensive review
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2019.04.188
– volume: 333
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0015
  article-title: A convolutional Transformer-based truncated Gaussian density network with data denoising for wind speed forecasting
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2022.120601
– volume: 21
  start-page: 1238
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0024
  article-title: Attention based Transformer coupled with convoluted neural network for ultra-short- and short-term forecasting of multiple wind farms
  publication-title: Int. J. Green Energy
  doi: 10.1080/15435075.2023.2244589
– volume: 206
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0030
  article-title: Short-term wind power forecasting based on attention mechanism and Deep learning
  publication-title: Electr. Power Syst. Res.
  doi: 10.1016/j.epsr.2022.107776
– volume: 284
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0033
  article-title: Renewable energy forecasting: a self-supervised learning-based transformer variant
  publication-title: Energy
  doi: 10.1016/j.energy.2023.128730
– volume: 76
  start-page: 637
  year: 2015
  ident: 10.1016/j.epsr.2025.111970_bib0010
  article-title: Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA
  publication-title: Renew. Energy
  doi: 10.1016/j.renene.2014.11.084
– volume: 15
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0020
  article-title: Enhancing sustainable urban energy management through short-term wind power forecasting using LSTM Neural network
  publication-title: Sustainability
  doi: 10.3390/su151813424
– volume: 23
  start-page: 13360
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0029
  article-title: Condition monitoring and fault detection of wind turbine driveline with the implementation of deep residual long short-term memory network
  publication-title: IEEE Sens. J.
  doi: 10.1109/JSEN.2023.3273279
– volume: 239
  year: 2025
  ident: 10.1016/j.epsr.2025.111970_bib0019
  article-title: Wind and solar power forecasting based on hybrid CNN-ABiLSTM, CNN-transformer-MLP models
  publication-title: Renew. Energy
  doi: 10.1016/j.renene.2024.122055
– volume: 153
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0035
  article-title: Robformer: a robust decomposition transformer for long-term time series forecasting
  publication-title: Pattern. Recognit.
  doi: 10.1016/j.patcog.2024.110552
– volume: 252
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0002
  article-title: Interpretable wind speed prediction with multivariate time series and temporal fusion transformers
  publication-title: Energy
  doi: 10.1016/j.energy.2022.123990
– volume: 242
  year: 2020
  ident: 10.1016/j.epsr.2025.111970_bib0011
  article-title: Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm
  publication-title: J. Clean. Prod.
  doi: 10.1016/j.jclepro.2019.118447
– volume: 2023
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0003
  article-title: A multistep direct and indirect strategy for predicting wind direction based on the EMD-LSTM model
  publication-title: Struct. Control Health Monit.
  doi: 10.1155/2023/4950487
– volume: 43
  start-page: 224
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0008
  article-title: Wind power prediction method based on spatial correlation andStacking ensemble learning
– volume: 290
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0031
  article-title: The univariate model for long-term wind speed forecasting based on wavelet soft threshold denoising and improved Autoformer
  publication-title: Energy
  doi: 10.1016/j.energy.2023.130225
– volume: 12
  start-page: 925
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0023
  article-title: Multistep forecasting method for offshore wind turbine power based on multi-timescale input and improved transformer
  publication-title: J. Mar. Sci. Eng.
  doi: 10.3390/jmse12060925
– volume: 261
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0040
  article-title: Multistep short-term wind speed forecasting using transformer
  publication-title: Energy
  doi: 10.1016/j.energy.2022.125231
– volume: 15
  start-page: 8417
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0001
  article-title: Research on multi-step prediction of short-term wind power based on combination model and error correction
  publication-title: Energies
  doi: 10.3390/en15228417
– volume: 25
  start-page: 4947
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0041
  article-title: WindTrans: transformer-based wind speed forecasting method for high-speed railway
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2023.3337150
– volume: 66
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0028
  article-title: Computation of prediction intervals of wind energy based on the EWMA and BOA techniques
  publication-title: Sustain. Energy Technol. Assess.
– volume: 106
  start-page: 7643
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0018
  article-title: Wind power prediction using optimized MLP-NN machine learning forecasting model
  publication-title: Electr. Eng.
  doi: 10.1007/s00202-024-02440-6
– volume: 32
  start-page: 981
  year: 2016
  ident: 10.1016/j.epsr.2025.111970_bib0025
  article-title: Short-term probabilistic forecasting of wind speed using stochastic differential equations
  publication-title: Int. J. Forecast.
  doi: 10.1016/j.ijforecast.2015.03.001
– volume: 11
  start-page: 906
  year: 2020
  ident: 10.1016/j.epsr.2025.111970_bib0009
  article-title: Ultra-short-term probabilistic wind turbine power forecast based on empirical dynamic modeling
  publication-title: IEEE Trans. Sustain. Energy
  doi: 10.1109/TSTE.2019.2912270
– volume: 15
  start-page: 951
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0032
  article-title: Time series analysis based on informer algorithms: a survey
  publication-title: Symmetry
  doi: 10.3390/sym15040951
– volume: 80
  start-page: 93
  year: 2019
  ident: 10.1016/j.epsr.2025.111970_bib0005
  article-title: A novel hybrid model for short-term wind power forecasting
  publication-title: Appl. Soft. Comput.
  doi: 10.1016/j.asoc.2019.03.035
– volume: 11
  start-page: 3247
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0022
  article-title: A novel hybrid deep learning model for forecasting Ultra-short-term time series wind speeds for wind turbines
  publication-title: Processes
  doi: 10.3390/pr11113247
– volume: 300
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0007
  article-title: A novel hybrid model based on empirical mode decomposition and echo state network for wind power forecasting
  publication-title: Energy
  doi: 10.1016/j.energy.2024.131546
– volume: 10
  start-page: 19621
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0036
  article-title: Transformer network for remaining useful life prediction of lithium-ion batteries
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2022.3151975
– volume: 319
  year: 2025
  ident: 10.1016/j.epsr.2025.111970_bib0013
  article-title: Optimization of deterministic and probabilistic forecasting for wind power based on ensemble learning
– volume: 312
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0037
  article-title: Integrating domain knowledge into transformer for short-term wind power forecasting
  publication-title: Energy
  doi: 10.1016/j.energy.2024.133511
– start-page: 372
  year: 2024
  ident: 10.1016/j.epsr.2025.111970_bib0039
  article-title: Autoregressive modeling of time series in renewable energy systems
– volume: 136
  start-page: 758
  year: 2019
  ident: 10.1016/j.epsr.2025.111970_bib0027
  article-title: Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting
  publication-title: Renew. Energy
  doi: 10.1016/j.renene.2019.01.031
– volume: 313
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0026
  article-title: Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2022.118801
– volume: 25
  start-page: 647
  year: 2023
  ident: 10.1016/j.epsr.2025.111970_bib0034
  article-title: An adaptive hybrid model for wind power prediction based on the IVMD-FE-Ad-Informer
  publication-title: Entropy
  doi: 10.3390/e25040647
– volume: 185
  start-page: 611
  year: 2022
  ident: 10.1016/j.epsr.2025.111970_bib0016
  article-title: Short-term offshore wind power forecasting - A hybrid model based on Discrete Wavelet Transform (DWT), Seasonal Autoregressive Integrated Moving Average (SARIMA), and deep-learning-based Long Short-Term Memory (LSTM)
  publication-title: Renew. Energy
  doi: 10.1016/j.renene.2021.12.100
– volume: 214
  year: 2021
  ident: 10.1016/j.epsr.2025.111970_bib0004
  article-title: Short-term wind power forecasting using the hybrid model of improved variational mode decomposition and Correntropy long Short -term memory neural network
  publication-title: Energy
  doi: 10.1016/j.energy.2020.118980
– volume: 11
  start-page: 559
  year: 2020
  ident: 10.1016/j.epsr.2025.111970_bib0012
  article-title: Application of hybrid forecast engine based intelligent algorithm and feature selection for wind signal prediction
  publication-title: Evol. Syst.
  doi: 10.1007/s12530-019-09271-y
– volume: 4
  start-page: 265
  year: 2016
  ident: 10.1016/j.epsr.2025.111970_bib0017
  article-title: Spatial dispersion of wind speeds and its influence on the forecasting error of wind power in a wind farm
  publication-title: J. Mod. Power Syst. Clean Energy
  doi: 10.1007/s40565-015-0151-x
SSID ssj0006975
Score 2.4690144
Snippet •A wind power forecasting method based on the time series Transformer model is proposed.•Novel model improves noisy data handling, time-series dependency...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 111970
SubjectTerms Seasonal trend decomposition
Sparse attention mechanism
Temporal autoencoder
Transformer
Wind power prediction
Title Short-term multi-step wind power prediction model based on Pt-Transformer neural network integrating spatio-temporal feature and sparse attention
URI https://dx.doi.org/10.1016/j.epsr.2025.111970
Volume 248
WOSCitedRecordID wos001521583400003&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: PRVESC
  databaseName: ScienceDirect Freedom Collection
  issn: 0378-7796
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0006975
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELbKLgc4IJ5ieckHbpVR6sR1clyhRYDQasUWVHGJbMfZZlWFqk2W5WfwW_iDjB9x0mpZsQcuUeI6jpv5Mh6Px98g9FplUulEFETKLCWJ5JKkkkoSwadUgMWhtE3n8_UTPz5O5_PsZDT63e2FuVjyuk4vL7PVfxU1lIGwzdbZG4g7NAoFcA5ChyOIHY7_JPjTBVjUxGhcFy1IQI6r8Y_KEAKYlGiGFqCoXIZwmwdnbEaywqwanDRk1hmyUNFwXYIEaxcpHpglrAfCBmITT2y1HJdahKUI-G29gdOmcaGUW85_m3WnUr4rjkfarFwMnGpDN_a3RfWzx-9pW7tCXUPpWYgdaq2_dw5IP1u01U7x57ZaaV_Zuzco8_v8ei0YwzSXc5f2tlPZ1LFzeqU7MUuh0ZXjgXNNnMPQvjHkr5S96Stvk2_vDIohVLGLgjvPTRu5aSN3bdxC-5SzDFTp_uGHo_nHYABMM8vvHHru92q5sMLdnlxtDw1snNl9dM9PTvChA9UDNNL1Q3R3QFn5CP3q4YV7eGEDL2xlint4YQsvbOGF4XIbXtjBC3t44QG88A68sIcXBnhhBy8c4PUYfXl3NHv7nvi0HkTFEW2INGt9KmZcwZSJcp4mSRyDGa0EzcppJDXoDi5EMi1jVlCmdcRppCeiKKmSESiQJ2iv_l7rpwj-ACu0gCaU0ImmTKZaxoViWRkxKTJ1gCbdy82V57w3qVeW-d_FeoDG4Z6VY3y5tjbrZJZ7m9XZojlA8Jr7nt3oKc_Rnf7beIH2mnWrX6Lb6qKpNutXHn9_ANKFw_I
linkProvider Elsevier
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=Short-term+multi-step+wind+power+prediction+model+based+on+Pt-Transformer+neural+network+integrating+spatio-temporal+feature+and+sparse+attention&rft.jtitle=Electric+power+systems+research&rft.au=Zhang%2C+Zhiyan&rft.au=Sun%2C+Zhenyang&rft.au=Guo%2C+Xianghui&rft.au=Guo%2C+Ruipeng&rft.date=2025-11-01&rft.issn=0378-7796&rft.volume=248&rft.spage=111970&rft_id=info:doi/10.1016%2Fj.epsr.2025.111970&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_epsr_2025_111970
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0378-7796&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0378-7796&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0378-7796&client=summon