An explainable multi-feature dimensionality reduction framework: Considering trend inconsistency in wind power sample
Offshore wind power prediction is significantly challenged by data quality issues arising from various factors such as environmental conditions and measurement errors, which severely compromise prediction accuracy and stability. This paper reveals a previously overlooked phenomenon in offshore wind...
Saved in:
| Published in: | Energy (Oxford) Vol. 336; p. 138466 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.11.2025
|
| Subjects: | |
| ISSN: | 0360-5442 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Offshore wind power prediction is significantly challenged by data quality issues arising from various factors such as environmental conditions and measurement errors, which severely compromise prediction accuracy and stability. This paper reveals a previously overlooked phenomenon in offshore wind power data, referred to as sample trend inconsistency, where dynamic offsets in meteorological features distort their expected physical relationship with power output. Such inconsistencies hinder the extraction of key features, disrupt feature–power coupling, and ultimately lead to degraded prediction performance. To address this issue, a Differential Compensation Dimensionality Reduction (DCDR) method is proposed to actively detect and mitigate trend inconsistencies during the dimensionality reduction process. Following normalized preprocessing of raw multi-feature meteorological data, the proposed DCDR method is employed to enhance sample trend consistency and perform dimensionality reduction by optimizing a selection coefficient to retain the most informative feature subset, which is then fed into deep learning models for training and accurate power forecasting. Experimental results demonstrate that DCDR achieves significant improvements over conventional dimensionality reduction methods, reducing RMSE and MAE by 21.1 % and 12.1 %, respectively. Furthermore, global feature importance analysis based on Shapley Additive Explanations (SHAP) confirms that the features retained by DCDR contribute more strongly to prediction accuracy and show improved consistency with the underlying physical relationships governing power output, thereby providing a more robust and interpretable framework that can enhance the operational reliability of offshore wind power forecasting models.
•First identification of trend inconsistency in offshore wind power data (over 45 % occurrence) caused by dynamic offsets.•Proposed a novel dimensionality reduction strategy to reduce prediction errors by 21.1 % (RMSE) and 12.1 % (MAE).•Robust generalization to high-dimensional data and complex environments with optimal dimensionality selection.•Constructed an interpretability driven feature selection framework in offshore wind power prediction. |
|---|---|
| AbstractList | Offshore wind power prediction is significantly challenged by data quality issues arising from various factors such as environmental conditions and measurement errors, which severely compromise prediction accuracy and stability. This paper reveals a previously overlooked phenomenon in offshore wind power data, referred to as sample trend inconsistency, where dynamic offsets in meteorological features distort their expected physical relationship with power output. Such inconsistencies hinder the extraction of key features, disrupt feature–power coupling, and ultimately lead to degraded prediction performance. To address this issue, a Differential Compensation Dimensionality Reduction (DCDR) method is proposed to actively detect and mitigate trend inconsistencies during the dimensionality reduction process. Following normalized preprocessing of raw multi-feature meteorological data, the proposed DCDR method is employed to enhance sample trend consistency and perform dimensionality reduction by optimizing a selection coefficient to retain the most informative feature subset, which is then fed into deep learning models for training and accurate power forecasting. Experimental results demonstrate that DCDR achieves significant improvements over conventional dimensionality reduction methods, reducing RMSE and MAE by 21.1 % and 12.1 %, respectively. Furthermore, global feature importance analysis based on Shapley Additive Explanations (SHAP) confirms that the features retained by DCDR contribute more strongly to prediction accuracy and show improved consistency with the underlying physical relationships governing power output, thereby providing a more robust and interpretable framework that can enhance the operational reliability of offshore wind power forecasting models.
•First identification of trend inconsistency in offshore wind power data (over 45 % occurrence) caused by dynamic offsets.•Proposed a novel dimensionality reduction strategy to reduce prediction errors by 21.1 % (RMSE) and 12.1 % (MAE).•Robust generalization to high-dimensional data and complex environments with optimal dimensionality selection.•Constructed an interpretability driven feature selection framework in offshore wind power prediction. |
| ArticleNumber | 138466 |
| Author | Huang, Ziqian Zhang, Qi Yin, Hao Liu, Honghui Xiao, Liexi Yan, Baiping Meng, Anbo Tan, Zhenglin |
| Author_xml | – sequence: 1 givenname: Anbo surname: Meng fullname: Meng, Anbo – sequence: 2 givenname: Honghui surname: Liu fullname: Liu, Honghui – sequence: 3 givenname: Liexi orcidid: 0000-0002-5960-6707 surname: Xiao fullname: Xiao, Liexi – sequence: 4 givenname: Zhenglin surname: Tan fullname: Tan, Zhenglin – sequence: 5 givenname: Ziqian surname: Huang fullname: Huang, Ziqian – sequence: 6 givenname: Qi surname: Zhang fullname: Zhang, Qi – sequence: 7 givenname: Baiping orcidid: 0000-0002-6511-9753 surname: Yan fullname: Yan, Baiping email: d_enip@163.com – sequence: 8 givenname: Hao surname: Yin fullname: Yin, Hao |
| BookMark | eNp9kM1OwzAQhH0oEm3hDTj4BRLs2HETDkhVxZ9UiQucLf9sKpfEiWyH0rcnVThzWs1oZ7T7rdDC9x4QuqMkp4SK-2MOHsLhnBekKHPKKi7EAi0JEyQrOS-u0SrGIyGkrOp6icatx_AztMp5pVvA3dgmlzWg0hgAW9eBj673qnXpjAPY0aRJ4iaoDk59-HrAu37asBCcP-AUwFvsvLl4MYE350nhk5vcoT9BwFF1Qws36KpRbYTbv7lGn89PH7vXbP_-8rbb7jNTlJuUmZKXJbGMF9QIwwmjXNcKGkqF2mhday4sEM0K4LqaNg3RorGs2XBWFUJotkZ87jWhjzFAI4fgOhXOkhJ5wSWPcsYlL7jkjGuKPc4xmG77dhBkNG56BqwLYJK0vfu_4BfMhnzE |
| Cites_doi | 10.1016/j.energy.2021.120185 10.1016/j.energy.2024.131458 10.1016/j.renene.2021.11.118 10.1016/j.energy.2021.122109 10.1016/j.lrp.2025.102511 10.3390/en15196942 10.1016/j.eswa.2023.121464 10.1016/j.energy.2019.116316 10.1016/j.engappai.2024.109628 10.1016/j.enconman.2023.116935 10.1038/s42254-020-00275-1 10.1016/j.energy.2022.126419 10.1109/TSTE.2018.2866543 10.1109/TPAMI.2024.3388092 10.1016/j.energy.2022.124957 10.1016/j.energy.2023.129139 10.1016/j.engappai.2024.109046 10.1146/annurev-fluid-030121-015835 10.1016/j.enconman.2024.118131 10.1016/j.rser.2015.09.063 10.1016/j.renene.2025.122951 10.1016/j.energy.2024.131030 10.1016/j.techfore.2024.123588 10.1016/j.energy.2020.118371 10.1016/j.apenergy.2018.10.080 10.1016/j.eswa.2025.127068 10.3390/electronics13122293 10.1016/j.energy.2024.132899 10.1016/j.egyai.2024.100442 10.1016/j.energy.2022.126503 10.1016/j.apenergy.2017.04.017 10.1007/s10462-015-9446-6 10.1109/TIP.2016.2549360 10.1016/j.apenergy.2019.04.188 10.1016/j.apenergy.2024.125174 10.1016/j.apenergy.2024.122624 10.1016/j.ijepes.2021.107042 10.1016/j.energy.2024.133510 10.1109/TGRS.2018.2828029 10.3390/jmse11101855 10.1016/j.renene.2022.09.036 10.3390/s22082822 10.1016/j.energy.2023.128226 10.1016/j.energy.2024.130770 10.1016/j.enconman.2017.06.021 10.1016/j.jclepro.2020.124628 10.1016/j.enconman.2024.118808 10.1016/j.rser.2020.109792 10.1016/j.apenergy.2024.124357 10.1016/j.apenergy.2021.118473 10.1016/j.energy.2024.133826 10.1016/j.enconman.2025.119752 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.energy.2025.138466 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Economics Environmental Sciences |
| ExternalDocumentID | 10_1016_j_energy_2025_138466 S0360544225041088 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AAEDT AAEDW AAHBH AAHCO AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AARJD AATTM AAXKI AAXUO AAYWO ABJNI ABMAC ACDAQ ACGFS ACIWK ACLOT ACRLP ACVFH ADBBV ADCNI ADEZE AEBSH AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFRAH AFTJW AGHFR AGUBO AGYEJ AHIDL AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP AXJTR BELTK BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS EFLBG 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 RNS ROL RPZ SDF SDG SES SEW SPC SPCBC SSR SSZ T5K TN5 XPP ZMT ~02 ~G- ~HD 29G 6TJ 9DU AAQXK AAYXX ABDPE ABFNM ABWVN ABXDB ACRPL ADMUD ADNMO ADXHL AGQPQ AHHHB ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB G-2 HVGLF HZ~ R2- SAC WUQ |
| ID | FETCH-LOGICAL-c257t-c54550d3421c6c40314b9aef116a7bb9b46de0b32e4b8550c0b6fd3f7438266b3 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001575510900011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0360-5442 |
| IngestDate | Thu Nov 27 00:48:25 EST 2025 Wed Dec 10 14:23:47 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Dimensionality reduction Sample trend inconsistency Differential compensation dimensionality reduction Abnormal data Offshore wind power prediction |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c257t-c54550d3421c6c40314b9aef116a7bb9b46de0b32e4b8550c0b6fd3f7438266b3 |
| ORCID | 0000-0002-5960-6707 0000-0002-6511-9753 |
| ParticipantIDs | crossref_primary_10_1016_j_energy_2025_138466 elsevier_sciencedirect_doi_10_1016_j_energy_2025_138466 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-11-01 2025-11-00 |
| PublicationDateYYYYMMDD | 2025-11-01 |
| PublicationDate_xml | – month: 11 year: 2025 text: 2025-11-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Energy (Oxford) |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Yan, Xing, Xia, Wang (bib39) Oct. 2024; 136 Zhu, Zhao, Shi, Yang, Zhou, Zeng (bib18) Dec. 2024; 312 Qian, Pei, Zareipour, Chen (bib21) Feb. 2019; 235 Liu, Chen (bib6) Sept. 2019; 249 Kirchner, Zec, Delibašić (bib29) Mar. 2016; 45 Han, Yang (bib44) Dec. 2023; 60 Ahmad, Zhang (bib9) Jan. 2022; 239 Zhang, Liu, Yan (bib3) Jan. 2024; 13 Zhao, Guo, Xiao, Wang, Chi, Guo (bib8) July 2017; 197 Yang (bib20) Feb. 2021; 283 Chen, Fu, Zhang, Shen, Wu (bib13) Nov. 2024; 308 Li (bib26) June 2025; 246 Kou (bib1) Jan. 2022; 22 Carlini, Del Pizzo, Giannuzzi, Lauria, Mottola, Pisani (bib48) Oct. 2021; 131 Yang, Wang, Zhang (bib15) Oct. 2023; 280 Hidalgo (bib25) Feb. 2021; 3 Yin, Ou, Huang, Meng (bib53) Dec. 2019; 189 Hu, Qiao, Liu, Zhu (bib30) July 2019; 10 Meng (bib5) Nov. 2023; 283 Schmid (bib23) Mar. 2022; 54 Zhang, Li, Zhang (bib27) Dec. 2020; 213 Liang, Zhang, Zhang, Hu (bib49) Dec. 2024; 313 Xiao, Zou, Chi, Fang (bib50) Mar. 2023; 267 Wu, Zheng, Guo, Liu (bib12) Nov. 2022; 199 Hu, Xiang, Huo, Jawad, Liu (bib43) June 2021; 224 Zheng, Li, Pan, Liu, Xia (bib2) Jan. 2016; 53 Liang, Tian (bib11) May 2025; 332 Cao, Wang, Liang, Hu (bib28) June 2024; 296 Han, Meng, Hu, Chu (bib7) Sept. 2017; 148 Jiang, Ma, Chen, Wang, Cai, Wang (bib22) Aug. 2018; 56 Xiong, Peng, Tao, Zhang, Song, Nazir (bib16) Mar. 2023; 266 Zhang, Wu, Cai (bib24) May 2016; 25 Dai, Yu, Leng (bib51) July 2024; 299 Buckley, Craig, Mudambi (bib31) Apr. 2025; 58 Liu, Wang, Qin, Fu, Shen (bib19) Jan. 2022; 15 Wang, Yang, Li, Ren, Li (bib32) May 2025; 275 Gharaee, Erfanimatin, Bahman (bib34) Sept. 2024; 315 Nematzadeh, García-Nieto, Hurtado, Aldana-Montes, Navas-Delgado (bib36) Jan. 2025; 139 Ahmed, Sreeram, Mishra, Arif (bib42) May 2020; 124 Meng (bib4) May 2023; 283 Mitrentsis, Lens (bib35) Mar. 2022; 309 Yin (bib46) Jan. 2025; 377 Li, Chong, Guo, Liu (bib14) Dec. 2024; 18 Shajalal, Boden, Stevens (bib38) Sept. 2024; 206 Joseph, Deo, Casillas-Pérez, Prasad, Raj, Salcedo-Sanz (bib40) Apr. 2024; 359 Masoumi (bib10) Oct. 2023; 11 Tian, Liu, Gan, Zhou, Wang, Ma (bib47) Mar. 2025; 381 Meng (bib17) Dec. 2022; 260 Cakiroglu, Demir, Hakan Ozdemir, Latif Aylak, Sariisik, Abualigah (bib41) Mar. 2024; 237 Yang, Han, Zhang, Wang (bib33) May 2024; 294 Sun, Li, Wang, Ma (bib52) Feb. 2024; 302 Morrison, Liu, Lin (bib45) Jan. 2022; 184 Zhuo, Ge (bib37) Nov. 2024; 46 Cakiroglu (10.1016/j.energy.2025.138466_bib41) 2024; 237 Wu (10.1016/j.energy.2025.138466_bib12) 2022; 199 Li (10.1016/j.energy.2025.138466_bib26) 2025; 246 Liang (10.1016/j.energy.2025.138466_bib11) 2025; 332 Cao (10.1016/j.energy.2025.138466_bib28) 2024; 296 Tian (10.1016/j.energy.2025.138466_bib47) 2025; 381 Meng (10.1016/j.energy.2025.138466_bib4) 2023; 283 Gharaee (10.1016/j.energy.2025.138466_bib34) 2024; 315 Li (10.1016/j.energy.2025.138466_bib14) 2024; 18 Masoumi (10.1016/j.energy.2025.138466_bib10) 2023; 11 Ahmed (10.1016/j.energy.2025.138466_bib42) 2020; 124 Yang (10.1016/j.energy.2025.138466_bib15) 2023; 280 Liu (10.1016/j.energy.2025.138466_bib19) 2022; 15 Zhu (10.1016/j.energy.2025.138466_bib18) 2024; 312 Liu (10.1016/j.energy.2025.138466_bib6) 2019; 249 Xiong (10.1016/j.energy.2025.138466_bib16) 2023; 266 Shajalal (10.1016/j.energy.2025.138466_bib38) 2024; 206 Zhuo (10.1016/j.energy.2025.138466_bib37) 2024; 46 Schmid (10.1016/j.energy.2025.138466_bib23) 2022; 54 Carlini (10.1016/j.energy.2025.138466_bib48) 2021; 131 Meng (10.1016/j.energy.2025.138466_bib17) 2022; 260 Morrison (10.1016/j.energy.2025.138466_bib45) 2022; 184 Yin (10.1016/j.energy.2025.138466_bib46) 2025; 377 Mitrentsis (10.1016/j.energy.2025.138466_bib35) 2022; 309 Yin (10.1016/j.energy.2025.138466_bib53) 2019; 189 Nematzadeh (10.1016/j.energy.2025.138466_bib36) 2025; 139 Han (10.1016/j.energy.2025.138466_bib44) 2023; 60 Zhang (10.1016/j.energy.2025.138466_bib24) 2016; 25 Han (10.1016/j.energy.2025.138466_bib7) 2017; 148 Yan (10.1016/j.energy.2025.138466_bib39) 2024; 136 Zheng (10.1016/j.energy.2025.138466_bib2) 2016; 53 Meng (10.1016/j.energy.2025.138466_bib5) 2023; 283 Joseph (10.1016/j.energy.2025.138466_bib40) 2024; 359 Hidalgo (10.1016/j.energy.2025.138466_bib25) 2021; 3 Yang (10.1016/j.energy.2025.138466_bib20) 2021; 283 Qian (10.1016/j.energy.2025.138466_bib21) 2019; 235 Chen (10.1016/j.energy.2025.138466_bib13) 2024; 308 Sun (10.1016/j.energy.2025.138466_bib52) 2024; 302 Kirchner (10.1016/j.energy.2025.138466_bib29) 2016; 45 Kou (10.1016/j.energy.2025.138466_bib1) 2022; 22 Hu (10.1016/j.energy.2025.138466_bib43) 2021; 224 Zhang (10.1016/j.energy.2025.138466_bib3) 2024; 13 Xiao (10.1016/j.energy.2025.138466_bib50) 2023; 267 Jiang (10.1016/j.energy.2025.138466_bib22) 2018; 56 Wang (10.1016/j.energy.2025.138466_bib32) 2025; 275 Ahmad (10.1016/j.energy.2025.138466_bib9) 2022; 239 Buckley (10.1016/j.energy.2025.138466_bib31) 2025; 58 Liang (10.1016/j.energy.2025.138466_bib49) 2024; 313 Zhang (10.1016/j.energy.2025.138466_bib27) 2020; 213 Hu (10.1016/j.energy.2025.138466_bib30) 2019; 10 Yang (10.1016/j.energy.2025.138466_bib33) 2024; 294 Dai (10.1016/j.energy.2025.138466_bib51) 2024; 299 Zhao (10.1016/j.energy.2025.138466_bib8) 2017; 197 |
| References_xml | – volume: 197 start-page: 183 year: July 2017 end-page: 202 ident: bib8 article-title: Multi-step wind speed and power forecasts based on a WRF simulation and an optimized association method publication-title: Appl Energy – volume: 13 year: Jan. 2024 ident: bib3 article-title: Research on the short-term prediction of offshore wind power based on unit classification publication-title: Electronics – volume: 260 year: Dec. 2022 ident: bib17 article-title: A novel wind power prediction approach using multivariate variational mode decomposition and multi-objective crisscross optimization based deep extreme learning machine publication-title: Energy – volume: 283 year: Nov. 2023 ident: bib5 article-title: A novel multi-gradient evolutionary deep learning approach for few-shot wind power prediction using time-series GAN publication-title: Energy – volume: 312 year: Dec. 2024 ident: bib18 article-title: A novel combined model based on advanced optimization algorithm, and deep learning model for abnormal wind speed identification and reconstruction publication-title: Energy – volume: 332 year: May 2025 ident: bib11 article-title: ISI net: a novel paradigm integrating interpretability and intelligent selection in ensemble learning for accurate wind power forecasting publication-title: Energy Convers Manag – volume: 283 year: Feb. 2021 ident: bib20 article-title: State-of-the-art one-stop handbook on wind forecasting technologies: an overview of classifications, methodologies, and analysis publication-title: J Clean Prod – volume: 308 year: Nov. 2024 ident: bib13 article-title: A novel offshore wind power prediction model based on TCN-DANet-sparse transformer and considering spatio-temporal coupling in multiple wind farms publication-title: Energy – volume: 224 year: June 2021 ident: bib43 article-title: An improved deep belief network based hybrid forecasting method for wind power publication-title: Energy – volume: 58 year: Apr. 2025 ident: bib31 article-title: Time and MNE strategy: managing temporal misalignments in global value chains publication-title: Long Range Plan – volume: 280 start-page: 128226 year: Oct. 2023 ident: bib15 article-title: A short-term wind power prediction method based on dynamic and static feature fusion mining publication-title: Energy – volume: 11 year: Oct. 2023 ident: bib10 article-title: Machine learning solutions for offshore wind farms: a review of applications and impacts publication-title: J Mar Sci Eng – volume: 237 year: Mar. 2024 ident: bib41 article-title: Data-driven interpretable ensemble learning methods for the prediction of wind turbine power incorporating SHAP analysis publication-title: Expert Syst Appl – volume: 206 year: Sept. 2024 ident: bib38 article-title: : explainable household energy demand forecasting by approximating shapley values using DeepLIFT publication-title: Technol Forecast Soc Change – volume: 53 start-page: 1240 year: Jan. 2016 end-page: 1251 ident: bib2 article-title: An overview of global ocean wind energy resource evaluations publication-title: Renew Sustain Energy Rev – volume: 266 year: Mar. 2023 ident: bib16 article-title: A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction publication-title: Energy – volume: 267 year: Mar. 2023 ident: bib50 article-title: Boosted GRU model for short-term forecasting of wind power with feature-weighted principal component analysis publication-title: Energy – volume: 56 start-page: 4581 year: Aug. 2018 end-page: 4593 ident: bib22 article-title: SuperPCA: a superpixelwise PCA approach for unsupervised feature extraction of hyperspectral imagery publication-title: IEEE Trans Geosci Remote Sensing – volume: 377 year: Jan. 2025 ident: bib46 article-title: Carbon emissions trading price forecasting based on temporal-spatial multidimensional collaborative attention network and segment imbalance regression publication-title: Appl Energy – volume: 302 year: Feb. 2024 ident: bib52 article-title: Modelling potential land suitability of large-scale wind energy development using explainable machine learning techniques: applications for China, USA and EU publication-title: Energy Convers Manag – volume: 184 start-page: 473 year: Jan. 2022 end-page: 486 ident: bib45 article-title: Anomaly detection in wind turbine SCADA data for power curve cleaning publication-title: Renew Energy – volume: 136 year: Oct. 2024 ident: bib39 article-title: Relation between fault characteristic frequencies and local interpretability shapley additive explanations for continuous machine health monitoring publication-title: Eng Appl Artif Intell – volume: 313 year: Dec. 2024 ident: bib49 article-title: A state-of-the-art analysis on decomposition method for short-term wind speed forecasting using LSTM and a novel hybrid deep learning model publication-title: Energy – volume: 54 start-page: 225 year: Mar. 2022 end-page: 254 ident: bib23 article-title: Dynamic mode decomposition and its variants publication-title: Annu Rev Fluid Mech – volume: 283 year: May 2023 ident: bib4 article-title: A novel network training approach for solving sample imbalance problem in wind power prediction publication-title: Energy Conv Manag – volume: 22 year: Jan. 2022 ident: bib1 article-title: Review on monitoring, operation and maintenance of smart offshore wind farms publication-title: Sensors – volume: 15 year: Jan. 2022 ident: bib19 article-title: A novel hybrid machine learning model for wind speed probabilistic forecasting publication-title: Energies – volume: 46 start-page: 7173 year: Nov. 2024 end-page: 7190 ident: bib37 article-title: IG2: integrated gradient on iterative gradient path for feature attribution publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 275 year: May 2025 ident: bib32 article-title: Data-driven deep learning model for short-term wind power prediction assisted with WGAN-GP data preprocessing publication-title: Expert Syst Appl – volume: 131 year: Oct. 2021 ident: bib48 article-title: Online analysis and prediction of the inertia in power systems with renewable power generation based on a minimum variance harmonic finite impulse response filter publication-title: Int J Electr Power Energy Syst – volume: 25 start-page: 2407 year: May 2016 ident: bib24 article-title: Compact representation of high-dimensional feature vectors for large-scale image recognition and retrieval publication-title: IEEE Trans Image Process – volume: 246 year: June 2025 ident: bib26 article-title: Short-term wind power prediction based on multiscale numerical simulation coupled with deep learning publication-title: Renew Energy – volume: 294 year: May 2024 ident: bib33 article-title: A short-term power prediction method for wind farm cluster based on the fusion of multi-source spatiotemporal feature information publication-title: Energy – volume: 299 year: July 2024 ident: bib51 article-title: A hybrid ensemble optimized BiGRU method for short-term photovoltaic generation forecasting publication-title: Energy – volume: 189 year: Dec. 2019 ident: bib53 article-title: A cascaded deep learning wind power prediction approach based on a two-layer of mode decomposition publication-title: Energy – volume: 213 year: Dec. 2020 ident: bib27 article-title: Short-term wind power forecasting approach based on Seq2Seq model using NWP data publication-title: Energy – volume: 45 start-page: 271 year: Mar. 2016 end-page: 297 ident: bib29 article-title: Facilitating data preprocessing by a generic framework: a proposal for clustering publication-title: Artif Intell Rev – volume: 381 year: Mar. 2025 ident: bib47 article-title: Short-term electric vehicle charging load forecasting based on TCN-LSTM network with comprehensive similar day identification publication-title: Appl Energy – volume: 60 year: Dec. 2023 ident: bib44 article-title: Correlation analysis based relevant variable selection for wind turbine condition monitoring and fault diagnosis publication-title: Sustain Energy Technol Assessments – volume: 249 start-page: 392 year: Sept. 2019 end-page: 408 ident: bib6 article-title: Data processing strategies in wind energy forecasting models and applications: a comprehensive review publication-title: Appl Energy – volume: 199 start-page: 977 year: Nov. 2022 end-page: 992 ident: bib12 article-title: Promoting wind energy for sustainable development by precise wind speed prediction based on graph neural networks publication-title: Renew Energy – volume: 10 start-page: 1330 year: July 2019 end-page: 1341 ident: bib30 article-title: Adaptive confidence boundary modeling of wind turbine power curve using SCADA data and its application publication-title: IEEE Trans Sustain Energy – volume: 239 year: Jan. 2022 ident: bib9 article-title: A data-driven deep sequence-to-sequence long-short memory method along with a gated recurrent neural network for wind power forecasting publication-title: Energy – volume: 309 year: Mar. 2022 ident: bib35 article-title: An interpretable probabilistic model for short-term solar power forecasting using natural gradient boosting publication-title: Appl Energy – volume: 148 start-page: 554 year: Sept. 2017 end-page: 568 ident: bib7 article-title: Non-parametric hybrid models for wind speed forecasting publication-title: Energy Convers Manag – volume: 315 year: Sept. 2024 ident: bib34 article-title: Machine learning development to predict the electrical efficiency of photovoltaic-thermal (PVT) collector systems publication-title: Energy Convers Manag – volume: 124 year: May 2020 ident: bib42 article-title: A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization publication-title: Renew Sustain Energy Rev – volume: 359 year: Apr. 2024 ident: bib40 article-title: Short-term wind speed forecasting using an optimized three-phase convolutional neural network fused with bidirectional long short-term memory network model publication-title: Appl Energy – volume: 139 year: Jan. 2025 ident: bib36 article-title: Model-agnostic local explanation: Multi-Objective genetic algorithm explainer publication-title: Eng Appl Artif Intell – volume: 296 year: June 2024 ident: bib28 article-title: A STAM-LSTM model for wind power prediction with feature selection publication-title: Energy – volume: 235 start-page: 939 year: Feb. 2019 end-page: 953 ident: bib21 article-title: A review and discussion of decomposition-based hybrid models for wind energy forecasting applications publication-title: Appl Energy – volume: 3 start-page: 92 year: Feb. 2021 end-page: 113 ident: bib25 article-title: Economic complexity theory and applications publication-title: Nat Rev Phys – volume: 18 year: Dec. 2024 ident: bib14 article-title: A hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction publication-title: Energy and AI – volume: 224 year: 2021 ident: 10.1016/j.energy.2025.138466_bib43 article-title: An improved deep belief network based hybrid forecasting method for wind power publication-title: Energy doi: 10.1016/j.energy.2021.120185 – volume: 299 year: 2024 ident: 10.1016/j.energy.2025.138466_bib51 article-title: A hybrid ensemble optimized BiGRU method for short-term photovoltaic generation forecasting publication-title: Energy doi: 10.1016/j.energy.2024.131458 – volume: 184 start-page: 473 year: 2022 ident: 10.1016/j.energy.2025.138466_bib45 article-title: Anomaly detection in wind turbine SCADA data for power curve cleaning publication-title: Renew Energy doi: 10.1016/j.renene.2021.11.118 – volume: 239 year: 2022 ident: 10.1016/j.energy.2025.138466_bib9 article-title: A data-driven deep sequence-to-sequence long-short memory method along with a gated recurrent neural network for wind power forecasting publication-title: Energy doi: 10.1016/j.energy.2021.122109 – volume: 58 issue: 2 year: 2025 ident: 10.1016/j.energy.2025.138466_bib31 article-title: Time and MNE strategy: managing temporal misalignments in global value chains publication-title: Long Range Plan doi: 10.1016/j.lrp.2025.102511 – volume: 15 issue: 19 year: 2022 ident: 10.1016/j.energy.2025.138466_bib19 article-title: A novel hybrid machine learning model for wind speed probabilistic forecasting publication-title: Energies doi: 10.3390/en15196942 – volume: 237 year: 2024 ident: 10.1016/j.energy.2025.138466_bib41 article-title: Data-driven interpretable ensemble learning methods for the prediction of wind turbine power incorporating SHAP analysis publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2023.121464 – volume: 189 year: 2019 ident: 10.1016/j.energy.2025.138466_bib53 article-title: A cascaded deep learning wind power prediction approach based on a two-layer of mode decomposition publication-title: Energy doi: 10.1016/j.energy.2019.116316 – volume: 139 year: 2025 ident: 10.1016/j.energy.2025.138466_bib36 article-title: Model-agnostic local explanation: Multi-Objective genetic algorithm explainer publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2024.109628 – volume: 283 year: 2023 ident: 10.1016/j.energy.2025.138466_bib4 article-title: A novel network training approach for solving sample imbalance problem in wind power prediction publication-title: Energy Conv Manag doi: 10.1016/j.enconman.2023.116935 – volume: 3 start-page: 92 issue: 2 year: 2021 ident: 10.1016/j.energy.2025.138466_bib25 article-title: Economic complexity theory and applications publication-title: Nat Rev Phys doi: 10.1038/s42254-020-00275-1 – volume: 266 year: 2023 ident: 10.1016/j.energy.2025.138466_bib16 article-title: A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction publication-title: Energy doi: 10.1016/j.energy.2022.126419 – volume: 60 year: 2023 ident: 10.1016/j.energy.2025.138466_bib44 article-title: Correlation analysis based relevant variable selection for wind turbine condition monitoring and fault diagnosis publication-title: Sustain Energy Technol Assessments – volume: 10 start-page: 1330 issue: 3 year: 2019 ident: 10.1016/j.energy.2025.138466_bib30 article-title: Adaptive confidence boundary modeling of wind turbine power curve using SCADA data and its application publication-title: IEEE Trans Sustain Energy doi: 10.1109/TSTE.2018.2866543 – volume: 46 start-page: 7173 issue: 11 year: 2024 ident: 10.1016/j.energy.2025.138466_bib37 article-title: IG2: integrated gradient on iterative gradient path for feature attribution publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2024.3388092 – volume: 260 year: 2022 ident: 10.1016/j.energy.2025.138466_bib17 article-title: A novel wind power prediction approach using multivariate variational mode decomposition and multi-objective crisscross optimization based deep extreme learning machine publication-title: Energy doi: 10.1016/j.energy.2022.124957 – volume: 283 year: 2023 ident: 10.1016/j.energy.2025.138466_bib5 article-title: A novel multi-gradient evolutionary deep learning approach for few-shot wind power prediction using time-series GAN publication-title: Energy doi: 10.1016/j.energy.2023.129139 – volume: 136 year: 2024 ident: 10.1016/j.energy.2025.138466_bib39 article-title: Relation between fault characteristic frequencies and local interpretability shapley additive explanations for continuous machine health monitoring publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2024.109046 – volume: 54 start-page: 225 year: 2022 ident: 10.1016/j.energy.2025.138466_bib23 article-title: Dynamic mode decomposition and its variants publication-title: Annu Rev Fluid Mech doi: 10.1146/annurev-fluid-030121-015835 – volume: 302 year: 2024 ident: 10.1016/j.energy.2025.138466_bib52 article-title: Modelling potential land suitability of large-scale wind energy development using explainable machine learning techniques: applications for China, USA and EU publication-title: Energy Convers Manag doi: 10.1016/j.enconman.2024.118131 – volume: 53 start-page: 1240 year: 2016 ident: 10.1016/j.energy.2025.138466_bib2 article-title: An overview of global ocean wind energy resource evaluations publication-title: Renew Sustain Energy Rev doi: 10.1016/j.rser.2015.09.063 – volume: 246 year: 2025 ident: 10.1016/j.energy.2025.138466_bib26 article-title: Short-term wind power prediction based on multiscale numerical simulation coupled with deep learning publication-title: Renew Energy doi: 10.1016/j.renene.2025.122951 – volume: 296 year: 2024 ident: 10.1016/j.energy.2025.138466_bib28 article-title: A STAM-LSTM model for wind power prediction with feature selection publication-title: Energy doi: 10.1016/j.energy.2024.131030 – volume: 206 year: 2024 ident: 10.1016/j.energy.2025.138466_bib38 article-title: ForecastExplainer: explainable household energy demand forecasting by approximating shapley values using DeepLIFT publication-title: Technol Forecast Soc Change doi: 10.1016/j.techfore.2024.123588 – volume: 213 year: 2020 ident: 10.1016/j.energy.2025.138466_bib27 article-title: Short-term wind power forecasting approach based on Seq2Seq model using NWP data publication-title: Energy doi: 10.1016/j.energy.2020.118371 – volume: 235 start-page: 939 year: 2019 ident: 10.1016/j.energy.2025.138466_bib21 article-title: A review and discussion of decomposition-based hybrid models for wind energy forecasting applications publication-title: Appl Energy doi: 10.1016/j.apenergy.2018.10.080 – volume: 275 year: 2025 ident: 10.1016/j.energy.2025.138466_bib32 article-title: Data-driven deep learning model for short-term wind power prediction assisted with WGAN-GP data preprocessing publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2025.127068 – volume: 13 issue: 12 year: 2024 ident: 10.1016/j.energy.2025.138466_bib3 article-title: Research on the short-term prediction of offshore wind power based on unit classification publication-title: Electronics doi: 10.3390/electronics13122293 – volume: 308 year: 2024 ident: 10.1016/j.energy.2025.138466_bib13 article-title: A novel offshore wind power prediction model based on TCN-DANet-sparse transformer and considering spatio-temporal coupling in multiple wind farms publication-title: Energy doi: 10.1016/j.energy.2024.132899 – volume: 18 year: 2024 ident: 10.1016/j.energy.2025.138466_bib14 article-title: A hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction publication-title: Energy and AI doi: 10.1016/j.egyai.2024.100442 – volume: 267 year: 2023 ident: 10.1016/j.energy.2025.138466_bib50 article-title: Boosted GRU model for short-term forecasting of wind power with feature-weighted principal component analysis publication-title: Energy doi: 10.1016/j.energy.2022.126503 – volume: 197 start-page: 183 year: 2017 ident: 10.1016/j.energy.2025.138466_bib8 article-title: Multi-step wind speed and power forecasts based on a WRF simulation and an optimized association method publication-title: Appl Energy doi: 10.1016/j.apenergy.2017.04.017 – volume: 45 start-page: 271 issue: 3 year: 2016 ident: 10.1016/j.energy.2025.138466_bib29 article-title: Facilitating data preprocessing by a generic framework: a proposal for clustering publication-title: Artif Intell Rev doi: 10.1007/s10462-015-9446-6 – volume: 25 start-page: 2407 issue: 5 year: 2016 ident: 10.1016/j.energy.2025.138466_bib24 article-title: Compact representation of high-dimensional feature vectors for large-scale image recognition and retrieval publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2016.2549360 – volume: 249 start-page: 392 year: 2019 ident: 10.1016/j.energy.2025.138466_bib6 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: 381 year: 2025 ident: 10.1016/j.energy.2025.138466_bib47 article-title: Short-term electric vehicle charging load forecasting based on TCN-LSTM network with comprehensive similar day identification publication-title: Appl Energy doi: 10.1016/j.apenergy.2024.125174 – volume: 359 year: 2024 ident: 10.1016/j.energy.2025.138466_bib40 article-title: Short-term wind speed forecasting using an optimized three-phase convolutional neural network fused with bidirectional long short-term memory network model publication-title: Appl Energy doi: 10.1016/j.apenergy.2024.122624 – volume: 131 year: 2021 ident: 10.1016/j.energy.2025.138466_bib48 article-title: Online analysis and prediction of the inertia in power systems with renewable power generation based on a minimum variance harmonic finite impulse response filter publication-title: Int J Electr Power Energy Syst doi: 10.1016/j.ijepes.2021.107042 – volume: 312 year: 2024 ident: 10.1016/j.energy.2025.138466_bib18 article-title: A novel combined model based on advanced optimization algorithm, and deep learning model for abnormal wind speed identification and reconstruction publication-title: Energy doi: 10.1016/j.energy.2024.133510 – volume: 56 start-page: 4581 issue: 8 year: 2018 ident: 10.1016/j.energy.2025.138466_bib22 article-title: SuperPCA: a superpixelwise PCA approach for unsupervised feature extraction of hyperspectral imagery publication-title: IEEE Trans Geosci Remote Sensing doi: 10.1109/TGRS.2018.2828029 – volume: 11 issue: 10 year: 2023 ident: 10.1016/j.energy.2025.138466_bib10 article-title: Machine learning solutions for offshore wind farms: a review of applications and impacts publication-title: J Mar Sci Eng doi: 10.3390/jmse11101855 – volume: 199 start-page: 977 year: 2022 ident: 10.1016/j.energy.2025.138466_bib12 article-title: Promoting wind energy for sustainable development by precise wind speed prediction based on graph neural networks publication-title: Renew Energy doi: 10.1016/j.renene.2022.09.036 – volume: 22 issue: 8 year: 2022 ident: 10.1016/j.energy.2025.138466_bib1 article-title: Review on monitoring, operation and maintenance of smart offshore wind farms publication-title: Sensors doi: 10.3390/s22082822 – volume: 280 start-page: 128226 year: 2023 ident: 10.1016/j.energy.2025.138466_bib15 article-title: A short-term wind power prediction method based on dynamic and static feature fusion mining publication-title: Energy doi: 10.1016/j.energy.2023.128226 – volume: 294 year: 2024 ident: 10.1016/j.energy.2025.138466_bib33 article-title: A short-term power prediction method for wind farm cluster based on the fusion of multi-source spatiotemporal feature information publication-title: Energy doi: 10.1016/j.energy.2024.130770 – volume: 148 start-page: 554 year: 2017 ident: 10.1016/j.energy.2025.138466_bib7 article-title: Non-parametric hybrid models for wind speed forecasting publication-title: Energy Convers Manag doi: 10.1016/j.enconman.2017.06.021 – volume: 283 year: 2021 ident: 10.1016/j.energy.2025.138466_bib20 article-title: State-of-the-art one-stop handbook on wind forecasting technologies: an overview of classifications, methodologies, and analysis publication-title: J Clean Prod doi: 10.1016/j.jclepro.2020.124628 – volume: 315 year: 2024 ident: 10.1016/j.energy.2025.138466_bib34 article-title: Machine learning development to predict the electrical efficiency of photovoltaic-thermal (PVT) collector systems publication-title: Energy Convers Manag doi: 10.1016/j.enconman.2024.118808 – volume: 124 year: 2020 ident: 10.1016/j.energy.2025.138466_bib42 article-title: A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization publication-title: Renew Sustain Energy Rev doi: 10.1016/j.rser.2020.109792 – volume: 377 year: 2025 ident: 10.1016/j.energy.2025.138466_bib46 article-title: Carbon emissions trading price forecasting based on temporal-spatial multidimensional collaborative attention network and segment imbalance regression publication-title: Appl Energy doi: 10.1016/j.apenergy.2024.124357 – volume: 309 year: 2022 ident: 10.1016/j.energy.2025.138466_bib35 article-title: An interpretable probabilistic model for short-term solar power forecasting using natural gradient boosting publication-title: Appl Energy doi: 10.1016/j.apenergy.2021.118473 – volume: 313 year: 2024 ident: 10.1016/j.energy.2025.138466_bib49 article-title: A state-of-the-art analysis on decomposition method for short-term wind speed forecasting using LSTM and a novel hybrid deep learning model publication-title: Energy doi: 10.1016/j.energy.2024.133826 – volume: 332 year: 2025 ident: 10.1016/j.energy.2025.138466_bib11 article-title: ISI net: a novel paradigm integrating interpretability and intelligent selection in ensemble learning for accurate wind power forecasting publication-title: Energy Convers Manag doi: 10.1016/j.enconman.2025.119752 |
| SSID | ssj0005899 |
| Score | 2.477443 |
| Snippet | Offshore wind power prediction is significantly challenged by data quality issues arising from various factors such as environmental conditions and measurement... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 138466 |
| SubjectTerms | Abnormal data Differential compensation dimensionality reduction Dimensionality reduction Offshore wind power prediction Sample trend inconsistency |
| Title | An explainable multi-feature dimensionality reduction framework: Considering trend inconsistency in wind power sample |
| URI | https://dx.doi.org/10.1016/j.energy.2025.138466 |
| Volume | 336 |
| WOSCitedRecordID | wos001575510900011&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: 0360-5442 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0005899 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3fq9MwFA66K-iL6NWL11_kwbdLRtukaePbkImKXASnDF9Kk6beXqS7rJvsz_ecpOlWr4gKvpQtrOnW85GenXzfdwh5wePY5DaqWWVkzoS2ESs51yxVmosytzJxu-ef32fn5_lyqT70O6adayeQtW2-26mr_xpqGINgo3T2L8I9TAoD8BqCDkcIOxz_KPAzZ9v_LaiiHGOQ1dYZeJ5VaObvjTgw_V6jcatnGwaSFpYIQhdP30PCOn8mg2Pdxik1G9R-o8EAtlg760p0GB6V-L2gEJ1Md548P5QbkEXriZR6NZCBmq17Aq7arxfbJowum3LlqwZ2NwwufL32y4VF-XF7WLNI0l68NxTSgphmz1zyAq6IpUKMFmfu7VGuLfS-5nA5te4HTfEi05hDMvWTr7Z7Un_EqXFm9GuLYV29SY6SLFX5hBzN3s6X7_akoNx1HB2-ShBbOkbg9Wv9Opk5SFAW98jd_p8FnXlE3Cc3bHtMbgfheXdMTuZ7USN8sF_VuwdkO2vpAWToCDJ0DBk6QIYOkHlJDwBDHWDoCDDwjiJgqAMM9YB5SD69ni9evWF9Ow5mYF3fMJOiAr7iIomNNAL7HmhV2jqOZZlprbSQlY00T6zQaJNnIi3ritcZ7jVLqfkJmbSr1j4iFJJMXcMckLzGIlVSlfAsqKoIJlZCWHlKWLivxZV3XSkCHfGy8HEoMA6Fj8MpycLNL_rM0WeEBeDlt2c-_uczn5A7e2g_JZPNemufkVvm-6bp1s97YP0A7IWZug |
| 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=An+explainable+multi-feature+dimensionality+reduction+framework%3A+Considering+trend+inconsistency+in+wind+power+sample&rft.jtitle=Energy+%28Oxford%29&rft.au=Meng%2C+Anbo&rft.au=Liu%2C+Honghui&rft.au=Xiao%2C+Liexi&rft.au=Tan%2C+Zhenglin&rft.date=2025-11-01&rft.pub=Elsevier+Ltd&rft.issn=0360-5442&rft.volume=336&rft_id=info:doi/10.1016%2Fj.energy.2025.138466&rft.externalDocID=S0360544225041088 |
| 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 |