Prediction indicators of unit 5 in KDD CUP.

<div><p>The accurate prediction of wind power is imperative for maintaining grid stability. In order to address the limitations of traditional neural network algorithms, the Informer model is employed for wind power prediction, delivering higher accuracy. However, due to insufficient exp...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Wenjuan Zhou (115285) (author)
مؤلفون آخرون: Feng Huang (62988) (author), Bing Wei (2588902) (author), Liang Li (46069) (author), Shixi Dai (22138931) (author), Xin Xie (311744) (author), Youyuan Peng (20862463) (author), Hong You (251402) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852017216223969280
author Wenjuan Zhou (115285)
author2 Feng Huang (62988)
Bing Wei (2588902)
Liang Li (46069)
Shixi Dai (22138931)
Xin Xie (311744)
Youyuan Peng (20862463)
Hong You (251402)
author2_role author
author
author
author
author
author
author
author_facet Wenjuan Zhou (115285)
Feng Huang (62988)
Bing Wei (2588902)
Liang Li (46069)
Shixi Dai (22138931)
Xin Xie (311744)
Youyuan Peng (20862463)
Hong You (251402)
author_role author
dc.creator.none.fl_str_mv Wenjuan Zhou (115285)
Feng Huang (62988)
Bing Wei (2588902)
Liang Li (46069)
Shixi Dai (22138931)
Xin Xie (311744)
Youyuan Peng (20862463)
Hong You (251402)
dc.date.none.fl_str_mv 2025-08-28T17:29:20Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0330464.t005
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Prediction_indicators_of_unit_5_in_KDD_CUP_/30003821
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biotechnology
Astronomical and Space Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
reduce computation time
maintaining grid stability
experimental results demonstrate
connected neural network
computational efficiency deteriorate
complex working conditions
characterizes equipment performance
blade deflection angle
hidden coupling model
delivering higher accuracy
wind turbine operation
dynamic synergistic coefficient
higher prediction accuracy
enhance prediction accuracy
traditional informer model
informer model based
wind turbine data
screen key multi
power prediction experiments
wind power prediction
prediction accuracy
informer model
wind power
wind speed
prediction framework
accurate prediction
maintenance data
informer ).
dynamic correlations
power output
xlink ">
study proposes
source features
new design
lasso algorithm
insufficient exploration
health matrix
health assessment
assessment yields
dc.title.none.fl_str_mv Prediction indicators of unit 5 in KDD CUP.
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <div><p>The accurate prediction of wind power is imperative for maintaining grid stability. In order to address the limitations of traditional neural network algorithms, the Informer model is employed for wind power prediction, delivering higher accuracy. However, due to insufficient exploration of dynamic coupling among multi-source features and inadequate data health status perception, both prediction accuracy and computational efficiency deteriorate under complex working conditions.This study proposes a prediction framework for the Informer model based on multi-source feature interaction optimization (MFIO-Informer). Integrating physical feature collaborative analysis with data health status perception has been shown to enhance prediction accuracy and reduce computation time. First, the Lasso algorithm and Pearson correlation coefficient method are applied to screen key multi-source features from wind turbine operation and maintenance data, quantifying their dynamic correlations with power output. Secondly, a fully-connected neural network (FNN) is employed to establish a hidden coupling model of wind speed, blade deflection angle, and power for extracting the Dynamic Synergistic Coefficient (DSC), which characterizes equipment performance. Subsequently, a health assessment of wind turbine data is conducted, leveraging historical power data and DSC. This assessment yields a health matrix, which is instrumental in optimizing the encoding, decoding, and embedding vector prediction processes of the Informer model. Finally, power prediction experiments are conducted on two public wind power datasets using the proposed MFIO-Informer model.The experimental results demonstrate that, in comparison with the traditional Informer model, the MFIO-Informer model attains approximately 20% higher prediction accuracy and 54.85% faster prediction speed.</p></div>
eu_rights_str_mv openAccess
id Manara_b4d1dd468ae2fbdf8a05b3a4b0fb0f7c
identifier_str_mv 10.1371/journal.pone.0330464.t005
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30003821
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Prediction indicators of unit 5 in KDD CUP.Wenjuan Zhou (115285)Feng Huang (62988)Bing Wei (2588902)Liang Li (46069)Shixi Dai (22138931)Xin Xie (311744)Youyuan Peng (20862463)Hong You (251402)BiotechnologyAstronomical and Space Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedreduce computation timemaintaining grid stabilityexperimental results demonstrateconnected neural networkcomputational efficiency deterioratecomplex working conditionscharacterizes equipment performanceblade deflection anglehidden coupling modeldelivering higher accuracywind turbine operationdynamic synergistic coefficienthigher prediction accuracyenhance prediction accuracytraditional informer modelinformer model basedwind turbine datascreen key multipower prediction experimentswind power predictionprediction accuracyinformer modelwind powerwind speedprediction frameworkaccurate predictionmaintenance datainformer ).dynamic correlationspower outputxlink ">study proposessource featuresnew designlasso algorithminsufficient explorationhealth matrixhealth assessmentassessment yields<div><p>The accurate prediction of wind power is imperative for maintaining grid stability. In order to address the limitations of traditional neural network algorithms, the Informer model is employed for wind power prediction, delivering higher accuracy. However, due to insufficient exploration of dynamic coupling among multi-source features and inadequate data health status perception, both prediction accuracy and computational efficiency deteriorate under complex working conditions.This study proposes a prediction framework for the Informer model based on multi-source feature interaction optimization (MFIO-Informer). Integrating physical feature collaborative analysis with data health status perception has been shown to enhance prediction accuracy and reduce computation time. First, the Lasso algorithm and Pearson correlation coefficient method are applied to screen key multi-source features from wind turbine operation and maintenance data, quantifying their dynamic correlations with power output. Secondly, a fully-connected neural network (FNN) is employed to establish a hidden coupling model of wind speed, blade deflection angle, and power for extracting the Dynamic Synergistic Coefficient (DSC), which characterizes equipment performance. Subsequently, a health assessment of wind turbine data is conducted, leveraging historical power data and DSC. This assessment yields a health matrix, which is instrumental in optimizing the encoding, decoding, and embedding vector prediction processes of the Informer model. Finally, power prediction experiments are conducted on two public wind power datasets using the proposed MFIO-Informer model.The experimental results demonstrate that, in comparison with the traditional Informer model, the MFIO-Informer model attains approximately 20% higher prediction accuracy and 54.85% faster prediction speed.</p></div>2025-08-28T17:29:20ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0330464.t005https://figshare.com/articles/dataset/Prediction_indicators_of_unit_5_in_KDD_CUP_/30003821CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/300038212025-08-28T17:29:20Z
spellingShingle Prediction indicators of unit 5 in KDD CUP.
Wenjuan Zhou (115285)
Biotechnology
Astronomical and Space Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
reduce computation time
maintaining grid stability
experimental results demonstrate
connected neural network
computational efficiency deteriorate
complex working conditions
characterizes equipment performance
blade deflection angle
hidden coupling model
delivering higher accuracy
wind turbine operation
dynamic synergistic coefficient
higher prediction accuracy
enhance prediction accuracy
traditional informer model
informer model based
wind turbine data
screen key multi
power prediction experiments
wind power prediction
prediction accuracy
informer model
wind power
wind speed
prediction framework
accurate prediction
maintenance data
informer ).
dynamic correlations
power output
xlink ">
study proposes
source features
new design
lasso algorithm
insufficient exploration
health matrix
health assessment
assessment yields
status_str publishedVersion
title Prediction indicators of unit 5 in KDD CUP.
title_full Prediction indicators of unit 5 in KDD CUP.
title_fullStr Prediction indicators of unit 5 in KDD CUP.
title_full_unstemmed Prediction indicators of unit 5 in KDD CUP.
title_short Prediction indicators of unit 5 in KDD CUP.
title_sort Prediction indicators of unit 5 in KDD CUP.
topic Biotechnology
Astronomical and Space Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
reduce computation time
maintaining grid stability
experimental results demonstrate
connected neural network
computational efficiency deteriorate
complex working conditions
characterizes equipment performance
blade deflection angle
hidden coupling model
delivering higher accuracy
wind turbine operation
dynamic synergistic coefficient
higher prediction accuracy
enhance prediction accuracy
traditional informer model
informer model based
wind turbine data
screen key multi
power prediction experiments
wind power prediction
prediction accuracy
informer model
wind power
wind speed
prediction framework
accurate prediction
maintenance data
informer ).
dynamic correlations
power output
xlink ">
study proposes
source features
new design
lasso algorithm
insufficient exploration
health matrix
health assessment
assessment yields