VMD-CNN-LSTM model architecture.

<div><p>This study focuses on the short-term power prediction of photovoltaic power stations, aiming to address the intermittent and fluctuating problems of photovoltaic power generation, in order to improve the prediction accuracy and ensure the stable operation of the power system. Inn...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Jiangli Yu (4601986) (author)
مؤلفون آخرون: Gaoyi Liang (22311429) (author), Lei Wang (6656) (author), Huiyuan He (22311432) (author), Yuxin Liu (505575) (author), Qi Liu (33068) (author), Xinjie Cui (498116) (author), Hao Wang (39217) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852016264989376512
author Jiangli Yu (4601986)
author2 Gaoyi Liang (22311429)
Lei Wang (6656)
Huiyuan He (22311432)
Yuxin Liu (505575)
Qi Liu (33068)
Xinjie Cui (498116)
Hao Wang (39217)
author2_role author
author
author
author
author
author
author
author_facet Jiangli Yu (4601986)
Gaoyi Liang (22311429)
Lei Wang (6656)
Huiyuan He (22311432)
Yuxin Liu (505575)
Qi Liu (33068)
Xinjie Cui (498116)
Hao Wang (39217)
author_role author
dc.creator.none.fl_str_mv Jiangli Yu (4601986)
Gaoyi Liang (22311429)
Lei Wang (6656)
Huiyuan He (22311432)
Yuxin Liu (505575)
Qi Liu (33068)
Xinjie Cui (498116)
Hao Wang (39217)
dc.date.none.fl_str_mv 2025-09-25T17:36:17Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0329821.g002
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/VMD-CNN-LSTM_model_architecture_/30211512
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biotechnology
Plant Biology
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
mean absolute error
decomposed modal components
solid data foundation
reduce data complexity
photovoltaic power stations
photovoltaic power generation
term power prediction
traditional prediction model
lstm combined model
kepler optimization algorithm
kepler algorithm
prediction accuracy
data preprocessing
power system
power changes
lstm leverages
xlink ">
three work
subsequent predictions
study focuses
strongly proves
stable operation
significant optimization
result correction
reliable method
proposed method
innovatively introduce
innovative idea
grid connection
great significance
frequency characteristics
fluctuating problems
evaluation indicators
entire process
dynamic trends
deeply integrated
dc.title.none.fl_str_mv VMD-CNN-LSTM model architecture.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>This study focuses on the short-term power prediction of photovoltaic power stations, aiming to address the intermittent and fluctuating problems of photovoltaic power generation, in order to improve the prediction accuracy and ensure the stable operation of the power system. Innovatively introduce the Kepler algorithm into this field, deeply analyze historical data, and mine the nonlinear relationships among various factors to lay a solid data foundation for subsequent predictions. The VMD-CNN-LSTM combined model is constructed. It is a model combining variational mode decomposition (VMD), convolutional neural network (CNN) and long short term memory network (LSTM), VMD adaptively decomposes the original power sequence based on frequency characteristics to reduce data complexity. CNN accurately extracts spatial features from the decomposed modal components; LSTM leverages its expertise in processing time series data to capture the dynamic trends of power changes, and the three work in synergy. Meanwhile, the Kepler optimization algorithm (KOA) is deeply integrated with this model to optimize the entire process of the model from data preprocessing to result correction. Verified by examples, compared with the traditional prediction model, the proposed method has significant optimization in evaluation indicators such as root mean square error and mean absolute error, which strongly proves its effectiveness and superiority. It provides an innovative idea and reliable method for the short-term power prediction of photovoltaic power stations and is of great significance for promoting the grid connection of photovoltaic power generation and the optimization of the power system.</p></div>
eu_rights_str_mv openAccess
id Manara_d5f7946d4f8975e6fcdbdce612dba03f
identifier_str_mv 10.1371/journal.pone.0329821.g002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30211512
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling VMD-CNN-LSTM model architecture.Jiangli Yu (4601986)Gaoyi Liang (22311429)Lei Wang (6656)Huiyuan He (22311432)Yuxin Liu (505575)Qi Liu (33068)Xinjie Cui (498116)Hao Wang (39217)BiotechnologyPlant BiologyBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedmean absolute errordecomposed modal componentssolid data foundationreduce data complexityphotovoltaic power stationsphotovoltaic power generationterm power predictiontraditional prediction modellstm combined modelkepler optimization algorithmkepler algorithmprediction accuracydata preprocessingpower systempower changeslstm leveragesxlink ">three worksubsequent predictionsstudy focusesstrongly provesstable operationsignificant optimizationresult correctionreliable methodproposed methodinnovatively introduceinnovative ideagrid connectiongreat significancefrequency characteristicsfluctuating problemsevaluation indicatorsentire processdynamic trendsdeeply integrated<div><p>This study focuses on the short-term power prediction of photovoltaic power stations, aiming to address the intermittent and fluctuating problems of photovoltaic power generation, in order to improve the prediction accuracy and ensure the stable operation of the power system. Innovatively introduce the Kepler algorithm into this field, deeply analyze historical data, and mine the nonlinear relationships among various factors to lay a solid data foundation for subsequent predictions. The VMD-CNN-LSTM combined model is constructed. It is a model combining variational mode decomposition (VMD), convolutional neural network (CNN) and long short term memory network (LSTM), VMD adaptively decomposes the original power sequence based on frequency characteristics to reduce data complexity. CNN accurately extracts spatial features from the decomposed modal components; LSTM leverages its expertise in processing time series data to capture the dynamic trends of power changes, and the three work in synergy. Meanwhile, the Kepler optimization algorithm (KOA) is deeply integrated with this model to optimize the entire process of the model from data preprocessing to result correction. Verified by examples, compared with the traditional prediction model, the proposed method has significant optimization in evaluation indicators such as root mean square error and mean absolute error, which strongly proves its effectiveness and superiority. It provides an innovative idea and reliable method for the short-term power prediction of photovoltaic power stations and is of great significance for promoting the grid connection of photovoltaic power generation and the optimization of the power system.</p></div>2025-09-25T17:36:17ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0329821.g002https://figshare.com/articles/figure/VMD-CNN-LSTM_model_architecture_/30211512CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/302115122025-09-25T17:36:17Z
spellingShingle VMD-CNN-LSTM model architecture.
Jiangli Yu (4601986)
Biotechnology
Plant Biology
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
mean absolute error
decomposed modal components
solid data foundation
reduce data complexity
photovoltaic power stations
photovoltaic power generation
term power prediction
traditional prediction model
lstm combined model
kepler optimization algorithm
kepler algorithm
prediction accuracy
data preprocessing
power system
power changes
lstm leverages
xlink ">
three work
subsequent predictions
study focuses
strongly proves
stable operation
significant optimization
result correction
reliable method
proposed method
innovatively introduce
innovative idea
grid connection
great significance
frequency characteristics
fluctuating problems
evaluation indicators
entire process
dynamic trends
deeply integrated
status_str publishedVersion
title VMD-CNN-LSTM model architecture.
title_full VMD-CNN-LSTM model architecture.
title_fullStr VMD-CNN-LSTM model architecture.
title_full_unstemmed VMD-CNN-LSTM model architecture.
title_short VMD-CNN-LSTM model architecture.
title_sort VMD-CNN-LSTM model architecture.
topic Biotechnology
Plant Biology
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
mean absolute error
decomposed modal components
solid data foundation
reduce data complexity
photovoltaic power stations
photovoltaic power generation
term power prediction
traditional prediction model
lstm combined model
kepler optimization algorithm
kepler algorithm
prediction accuracy
data preprocessing
power system
power changes
lstm leverages
xlink ">
three work
subsequent predictions
study focuses
strongly proves
stable operation
significant optimization
result correction
reliable method
proposed method
innovatively introduce
innovative idea
grid connection
great significance
frequency characteristics
fluctuating problems
evaluation indicators
entire process
dynamic trends
deeply integrated