Residual-corrected TSMixer with a RIME-enhanced decomposition strategy for photovoltaic power prediction

•Proposes a RIME-enhanced two-stage decomposition for deep feature extraction.•Bayesian optimization and residual correction enhance the model’s performance.•The model’s excellent balance of accuracy and efficiency is verified by experiments. To address the challenges of volatility and uncertainty i...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Electric power systems research Ročník 253
Hlavní autori: Cao, Lipeng, Shao, Xing, Wang, Cuixiang, Gao, Jun
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.04.2026
Predmet:
ISSN:0378-7796
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •Proposes a RIME-enhanced two-stage decomposition for deep feature extraction.•Bayesian optimization and residual correction enhance the model’s performance.•The model’s excellent balance of accuracy and efficiency is verified by experiments. To address the challenges of volatility and uncertainty in photovoltaic (PV) power prediction, this paper proposes a hybrid prediction model based on two-stage decomposition and residual correction (RC). The model first employs Variational Mode Decomposition (VMD), optimized by the RIME algorithm, for primary decomposition, followed by secondary decomposition of the resulting high-frequency residuals using Complete Ensemble EMD with Adaptive Noise (CEEMDAN) to achieve deep feature extraction. Subsequently, a TSMixer model, fine-tuned by the Bayesian Optimization Algorithm (BOA), is used to predict each component. Finally, the prediction results are rectified through an error correction mechanism. Comprehensive experiments based on datasets from multiple sites with diverse climatic conditions–including Alice Springs and Yulara in Australia, and Xinjiang in China–show that the proposed model demonstrates significant performance advantages over several comparative models, validating its effectiveness, robustness, and generalizability in complex PV power prediction tasks.
AbstractList •Proposes a RIME-enhanced two-stage decomposition for deep feature extraction.•Bayesian optimization and residual correction enhance the model’s performance.•The model’s excellent balance of accuracy and efficiency is verified by experiments. To address the challenges of volatility and uncertainty in photovoltaic (PV) power prediction, this paper proposes a hybrid prediction model based on two-stage decomposition and residual correction (RC). The model first employs Variational Mode Decomposition (VMD), optimized by the RIME algorithm, for primary decomposition, followed by secondary decomposition of the resulting high-frequency residuals using Complete Ensemble EMD with Adaptive Noise (CEEMDAN) to achieve deep feature extraction. Subsequently, a TSMixer model, fine-tuned by the Bayesian Optimization Algorithm (BOA), is used to predict each component. Finally, the prediction results are rectified through an error correction mechanism. Comprehensive experiments based on datasets from multiple sites with diverse climatic conditions–including Alice Springs and Yulara in Australia, and Xinjiang in China–show that the proposed model demonstrates significant performance advantages over several comparative models, validating its effectiveness, robustness, and generalizability in complex PV power prediction tasks.
ArticleNumber 112554
Author Cao, Lipeng
Shao, Xing
Wang, Cuixiang
Gao, Jun
Author_xml – sequence: 1
  givenname: Lipeng
  orcidid: 0009-0001-6333-357X
  surname: Cao
  fullname: Cao, Lipeng
– sequence: 2
  givenname: Xing
  orcidid: 0000-0001-8148-9984
  surname: Shao
  fullname: Shao, Xing
  email: shaoxing269@sina.com
– sequence: 3
  givenname: Cuixiang
  orcidid: 0009-0008-4018-8358
  surname: Wang
  fullname: Wang, Cuixiang
– sequence: 4
  givenname: Jun
  orcidid: 0009-0000-6107-4327
  surname: Gao
  fullname: Gao, Jun
BookMark eNotkN9OwjAUxnuBiYC-gFd9gc12o-2WeGMIKgnEBPG6Ke2p64Lr0lbQt2cLXp2L7-T785uhSec7QOiBkpwSyh_bHPoY8oIULKe0YGwxQVNSiioToua3aBZjSwjhtWBT1OwgOvOjjpn2IYBOYPD-Y-t-IeCzSw1WeLferjLoGtXpQTSg_Xfvo0vOdzimoBJ8_WHrA-4bn_zJH5NyGvf-PFj0AYzT4-sdurHqGOH-_87R58tqv3zLNu-v6-XzJoOhasoqU1NVqLI6mJozoohitrbCGgbCaAEMSgNwEAvFGHCoKRDLqLGac1IAiHKOnq6-MIScHAQZtYOxuhvnSeOdpESOpGQrR1JyJCWvpMoLwu9lvg
ContentType Journal Article
Copyright 2025
Copyright_xml – notice: 2025
DOI 10.1016/j.epsr.2025.112554
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID S0378779625011411
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
ID FETCH-LOGICAL-e125t-8d91a2a38bd9650a0a5f9f7fd5e7dc7e5e3deeb74a55e6e91e0f51dfc6602ee73
ISSN 0378-7796
IngestDate Wed Dec 10 14:24:58 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Two-stage decomposition
Photovoltaic power prediction
Bayesian optimization algorithm
TSMixer
Residual correction
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-e125t-8d91a2a38bd9650a0a5f9f7fd5e7dc7e5e3deeb74a55e6e91e0f51dfc6602ee73
ORCID 0009-0000-6107-4327
0000-0001-8148-9984
0009-0008-4018-8358
0009-0001-6333-357X
ParticipantIDs elsevier_sciencedirect_doi_10_1016_j_epsr_2025_112554
PublicationCentury 2000
PublicationDate April 2026
PublicationDateYYYYMMDD 2026-04-01
PublicationDate_xml – month: 04
  year: 2026
  text: April 2026
PublicationDecade 2020
PublicationTitle Electric power systems research
PublicationYear 2026
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Wang, Ma (bib0023) 2024; 295
Zhou, Liu, Wang, Wang, Jia (bib0022) 2025
Ahmed, Sreeram, Togneri, Datta, Arif (bib0015) 2022; 258
Zhang, Peng, Nazir (bib0024) 2022; 213
Zarzycki, Ławryńczuk (bib0016) 2022; 616
Hassan, Hsu, Mounich, Algburi, Jaszczur, Telba, Viktor, Awwad, Ahsan, Ali (bib0003) 2024; 66
Peng, Fu, Wang, Xiong, Suo, Nazir, Zhang (bib0031) 2023; 78
Polasek, Čadík (bib0008) 2023; 339
Zhu, Ren, Gu, Zhang, Sun (bib0004) 2023; 147
Agga, Abbou, Labbadi, El Houm, Ali (bib0014) 2022; 208
Yu, Niu, Wang, Du, Yu, Sun, Wang (bib0009) 2023; 275
Wu, Hu, Zhu, Jiang, Lv, Dong, Zhang (bib0011) 2024; 288
Gong, Qu, Zhu, Xu (bib0020) 2025; 320
Bai, Shi, Yue, Du (bib0007) 2023; 6
Lin, Zhang, Li, Lu (bib0025) 2022; 504
Su, Zhao, Heidari, Liu, Zhang, Mafarja, Chen (bib0033) 2023; 532
Tian, Ooka, Lee (bib0002) 2023; 426
Shang, Sang, Tiwari, Khan, Zhao (bib0001) 2024; 362
Li, Song, Wang, Wang, Jia (bib0028) 2022; 251
Diebold, Mariano (bib0036) 2002; 20
Li, Zhang, Ma, Jiao, Wang, Hu (bib0010) 2021; 224
Pelikan (bib0034) 2005
Zhang, Sun, Guo, Lu (bib0030) 2025; 243
Wang, Yan, Li, Zhang, Jiang, Yang, Li, Li, Zhang, Wang (bib0026) 2024; 236
Peng, Song, Suo, Wang, Nazir, Zhang (bib0005) 2024; 308
Chen, Peng, Qian, Ge, Wang, Nazir, Zhang (bib0019) 2025; 377
Kim, Obregon, Park, Jung (bib0018) 2024; 200
Zhang, Lv, Ma, Zhao, Wang, O’Hare (bib0021) 2020; 397
Sun, Liu (bib0032) 2024; 305
Hou, Zhang, Liu, Ye (bib0013) 2024; 11
Nguyen, Phan (bib0027) 2022; 8
Zhuo, Ni, Xiao (bib0029) 2024; 39
Huang, Li, Tai, Chen, Liu, Shi, Liu (bib0017) 2022; 246
Chen, Li, Arik, Yoder, Pfister (bib0035) 2023
Jiang, Ding, Chen, Cui, Zhang, Yang, Cang, Cao (bib0006) 2024; 308
Yang, Huang (bib0012) 2018; 6
References_xml – volume: 362
  year: 2024
  ident: bib0001
  article-title: Impacts of renewable energy on climate risk: a global perspective for energy transition in a climate adaptation framework
  publication-title: Appl. Energy
– volume: 243
  year: 2025
  ident: bib0030
  article-title: Short-term photovoltaic power prediction with CPO-BILSTM based on quadratic decomposition
  publication-title: Electr. Power Syst. Res.
– volume: 246
  year: 2022
  ident: bib0017
  article-title: Time series forecasting for hourly photovoltaic power using conditional generative adversarial network and Bi-LSTM
  publication-title: Energy
– volume: 11
  start-page: 5125
  year: 2024
  end-page: 5138
  ident: bib0013
  article-title: A hybrid machine learning forecasting model for photovoltaic power
  publication-title: Energy Rep.
– volume: 426
  year: 2023
  ident: bib0002
  article-title: Multi-scale solar radiation and photovoltaic power forecasting with machine learning algorithms in urban environment: a state-of-the-art review
  publication-title: J. Clean. Prod.
– volume: 616
  start-page: 229
  year: 2022
  end-page: 254
  ident: bib0016
  article-title: Advanced predictive control for GRU and LSTM networks
  publication-title: Inf. Sci.
– volume: 20
  start-page: 134
  year: 2002
  end-page: 144
  ident: bib0036
  article-title: Comparing predictive accuracy
  publication-title: J. Bus. Econ. Stat.
– volume: 377
  year: 2025
  ident: bib0019
  article-title: An error-corrected deep autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction
  publication-title: Appl. Energy
– volume: 532
  start-page: 183
  year: 2023
  end-page: 214
  ident: bib0033
  article-title: RIME: A physics-based optimization
  publication-title: Neurocomputing
– volume: 397
  start-page: 438
  year: 2020
  end-page: 446
  ident: bib0021
  article-title: A photovoltaic power forecasting model based on dendritic neuron networks with the aid of wavelet transform
  publication-title: Neurocomputing
– year: 2023
  ident: bib0035
  article-title: TSMixer: an all-MLP architecture for time series forecast-ing
  publication-title: Trans. Mach. Learn. Res.
– volume: 275
  year: 2023
  ident: bib0009
  article-title: Short-term photovoltaic power point-interval forecasting based on double-layer decomposition and WOA-BiLSTM-Attention and considering weather classification
  publication-title: Energy
– volume: 320
  year: 2025
  ident: bib0020
  article-title: Parallel TimesNet-BiLSTM model for ultra-short-term photovoltaic power forecasting using STL decomposition and auto-tuning
  publication-title: Energy
– volume: 66
  year: 2024
  ident: bib0003
  article-title: Enhancing smart grid integrated renewable distributed generation capacities: implications for sustainable energy transformation
  publication-title: Sustain. Energy Technol. Assess.
– volume: 504
  start-page: 56
  year: 2022
  end-page: 67
  ident: bib0025
  article-title: Multi-step prediction of photovoltaic power based on two-stage decomposition and BILSTM
  publication-title: Neurocomputing
– volume: 78
  year: 2023
  ident: bib0031
  article-title: An intelligent hybrid approach for photovoltaic power forecasting using enhanced chaos game optimization algorithm and locality sensitive hashing based informer model
  publication-title: J. Build. Eng.
– year: 2005
  ident: bib0034
  article-title: Bayesian optimization algorithm
  publication-title: Hierarchical Bayesian optimization algorithm: toward a new generation of evolutionary algorithms
– volume: 251
  year: 2022
  ident: bib0028
  article-title: A novel offshore wind farm typhoon wind speed prediction model based on PSO–Bi-LSTM improved by VMD
  publication-title: Energy
– volume: 258
  year: 2022
  ident: bib0015
  article-title: Computationally expedient photovoltaic power forecasting: a LSTM ensemble method augmented with adaptiveweighting and data segmentation technique
  publication-title: Energy Convers. Manag.
– volume: 39
  start-page: 80
  year: 2024
  end-page: 88
  ident: bib0029
  article-title: Single-parameter time series prediction method for thermal systems based on GWO-VMD-LSTM
  publication-title: Therm. Eng.
– volume: 6
  start-page: 51200
  year: 2018
  end-page: 51205
  ident: bib0012
  article-title: Ultra-short-term prediction of photovoltaic power based on periodic extraction of PV energy and LSH algorithm
  publication-title: IEEE Access
– volume: 200
  year: 2024
  ident: bib0018
  article-title: Multi-step photovoltaic power forecasting using transformer and recurrent neural networks
  publication-title: Renew. Sustain. Energy Rev.
– volume: 208
  year: 2022
  ident: bib0014
  article-title: CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production
  publication-title: Electr. Power Syst. Res.
– volume: 288
  year: 2024
  ident: bib0011
  article-title: Combined IXGBoost-KELM short-term photovoltaic power prediction model based on multidimensional similar day clustering and dual decomposition
  publication-title: Energy
– volume: 224
  year: 2021
  ident: bib0010
  article-title: A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine
  publication-title: Energy
– volume: 295
  year: 2024
  ident: bib0023
  article-title: A hybrid deep learning model with an optimal strategy based on improved VMD and transformer for short-term photovoltaic power forecasting
  publication-title: Energy
– year: 2025
  ident: bib0022
  article-title: Combined ultra-short-term photovoltaic power prediction based on CEEMDAN decomposition and RIME optimized AM-TCN-BiLSTM
  publication-title: Energy
– volume: 147
  year: 2023
  ident: bib0004
  article-title: Economic dispatching of wind/photovoltaic/storage considering load supply reliability and maximize capacity utilization
  publication-title: Int. J. Electr. Power Energy Syst.
– volume: 213
  year: 2022
  ident: bib0024
  article-title: A novel integrated photovoltaic power forecasting model based on variational mode decomposition and CNN-BiGRU considering meteorological variables
  publication-title: Electr. Power Syst. Res.
– volume: 236
  year: 2024
  ident: bib0026
  article-title: Short-term prediction of photovoltaic power based on quadratic decomposition and residual correction
  publication-title: Electr. Power Syst. Res.
– volume: 339
  year: 2023
  ident: bib0008
  article-title: Predicting photovoltaic power production using high-uncertainty weather forecasts
  publication-title: Appl. Energy
– volume: 6
  start-page: 184
  year: 2023
  end-page: 196
  ident: bib0007
  article-title: Hybrid model based on K-means++ algorithm, optimal similar day approach, and long short-term memory neural network for short-term photovoltaic power prediction
  publication-title: Global Energy Interconnection
– volume: 308
  year: 2024
  ident: bib0006
  article-title: Research on time-series based and similarity search based methods for PV power prediction
  publication-title: Energy Convers. Manag.
– volume: 305
  year: 2024
  ident: bib0032
  article-title: Multivariate short-term wind speed prediction based on PSO-VMD-SE-ICEEMDAN two-stage decomposition and Att-S2S
  publication-title: Energy
– volume: 308
  year: 2024
  ident: bib0005
  article-title: Research and application of a novel graph convolutional RVFL and evolutionary equilibrium optimizer algorithm considering spatial factors in ultra-short-term solar power prediction
  publication-title: Energy
– volume: 8
  start-page: 53
  year: 2022
  end-page: 60
  ident: bib0027
  article-title: Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization
  publication-title: Energy Rep.
SSID ssj0006975
Score 2.463901
Snippet •Proposes a RIME-enhanced two-stage decomposition for deep feature extraction.•Bayesian optimization and residual correction enhance the model’s...
SourceID elsevier
SourceType Publisher
SubjectTerms Bayesian optimization algorithm
Photovoltaic power prediction
Residual correction
TSMixer
Two-stage decomposition
Title Residual-corrected TSMixer with a RIME-enhanced decomposition strategy for photovoltaic power prediction
URI https://dx.doi.org/10.1016/j.epsr.2025.112554
Volume 253
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  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/eLvHCXMwtV3Na9swFBeh7WE7lK7bWD82dNgtGOIPWdaxlPSLtow2Y7kZVXoiLsUJiVPy5_fJkh23uWyDXowRtmL0-0V6enrv9wj5KRK0IVKTBVrh3y2JIhPIVIaBElwl2iRGmVpd_5rf3mbjsfjV65kmF-b5iZdltlqJ2btCjW0Itk2d_Qe4206xAe8RdLwi7Hj9K-DvYFEnWAXKFt5Q1qIc3d8UK5j7RLb-3eXNMIBy4g7_Ndiwch-71V84tVoXxjmbTKspzl-VLFR_ZuupWU0BXagWzcanXxfTaR9y8tD2QKLjK6sPOqbODzADv2DW4pCudVys2_54L_bpslghf9v2c_fo1bLseiuitBPkUrvQNtJoXOoWbmU5d6Vtm2k5ciLCG1O88zY84mq9sHquEbNZUMwpUb-Rzr63Hdt-0c7DfZ9NAd-OOBM4gW-fXA7HV-2anYpakrn9EJ9e5SIB3_5Sx27p2CKjPbLrNxH0xIH_ifSg3CcfO9KSn8lkkwbU04BaGlBJX9GAvqIBbWhAkQa0SwNaI0zXNPhCfp8NR6cXga-qEQB-fRVkWoQyknH2oAWa53IgmRGGG82Aa8WBQawBHngiGYMURAgDw0JtVJoOIgAefyVb5bSEb4TGxp7C6ziFME6sbJI0DASTDLflCd4cENYMVO4NOmeo5Qhm3sQXPuZ2gHM7wLkb4MP_fO-IfFhz7phsVfMlfCc76rkqFvMfHvMXLft15A
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=Residual-corrected+TSMixer+with+a+RIME-enhanced+decomposition+strategy+for+photovoltaic+power+prediction&rft.jtitle=Electric+power+systems+research&rft.au=Cao%2C+Lipeng&rft.au=Shao%2C+Xing&rft.au=Wang%2C+Cuixiang&rft.au=Gao%2C+Jun&rft.date=2026-04-01&rft.pub=Elsevier+B.V&rft.issn=0378-7796&rft.volume=253&rft_id=info:doi/10.1016%2Fj.epsr.2025.112554&rft.externalDocID=S0378779625011411
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