EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and application

Wind power prediction is critical for the efficient utilization of wind energy and the stable operation of power grids. However, existing prediction methods struggle to handle the complex characteristics of meteorological data. To address this challenge, this paper proposes an entropy-driven high-di...

Full description

Saved in:
Bibliographic Details
Main Authors: Xing Liu, Xingyu Mou, Ying Zhang, Hui Chen, Xin Wang, Xihao Sun, Chengcheng Wang, Ruixiang Shong, Yunfeng Li
Format: Article
Language:English
Published: AIP Publishing LLC 2025-06-01
Series:AIP Advances
Online Access:http://dx.doi.org/10.1063/5.0268894
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710139391606784
author Xing Liu
Xingyu Mou
Ying Zhang
Hui Chen
Xin Wang
Xihao Sun
Chengcheng Wang
Ruixiang Shong
Yunfeng Li
author_facet Xing Liu
Xingyu Mou
Ying Zhang
Hui Chen
Xin Wang
Xihao Sun
Chengcheng Wang
Ruixiang Shong
Yunfeng Li
author_sort Xing Liu
collection DOAJ
description Wind power prediction is critical for the efficient utilization of wind energy and the stable operation of power grids. However, existing prediction methods struggle to handle the complex characteristics of meteorological data. To address this challenge, this paper proposes an entropy-driven high-dimensional feature gain XGBoost model. First, traditional meteorological data are transformed into information entropy from an informational perspective, enabling the capture of randomness and nonlinear relationships within the data. Next, an entropy-driven high-dimensional (EDHD) classification feature selection method is designed to identify the relationships between covariates and response variables in the information entropy. Subsequently, a feature-gain XGBoost model is constructed to dynamically determine the optimal splitting features and thresholds, achieving the entropy-driven high-dimensional feature gain XGBoost model (EDHD-FG-XGBoost). Finally, experiments using real wind farm data from the northeastern region of China demonstrate the feasibility and effectiveness of the proposed method.
format Article
id doaj-art-40ba84142dd44294a2c608ad5aca8554
institution DOAJ
issn 2158-3226
language English
publishDate 2025-06-01
publisher AIP Publishing LLC
record_format Article
series AIP Advances
spelling doaj-art-40ba84142dd44294a2c608ad5aca85542025-08-20T03:14:59ZengAIP Publishing LLCAIP Advances2158-32262025-06-01156065022065022-1210.1063/5.0268894EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and applicationXing Liu0Xingyu Mou1Ying Zhang2Hui Chen3Xin Wang4Xihao Sun5Chengcheng Wang6Ruixiang Shong7Yunfeng Li8National University of Singapore, 21 Lower Kent Ridge Rd., Singapore 119077Jilin Province Meteorological Information Network Center, Jilin Province, Changchun 130062, ChinaJilin Province Meteorological Information Network Center, Jilin Province, Changchun 130062, ChinaJilin Province Meteorological Information Network Center, Jilin Province, Changchun 130062, ChinaJilin Province Forestry Information Center, Jilin Province, Changchun 130022, ChinaDalian Ocean University, Liaoning, Dalian 116023, ChinaJilin Province Meteorological Information Network Center, Jilin Province, Changchun 130062, ChinaJilin Province Meteorological Information Network Center, Jilin Province, Changchun 130062, ChinaJilin Province Meteorological Information Network Center, Jilin Province, Changchun 130062, ChinaWind power prediction is critical for the efficient utilization of wind energy and the stable operation of power grids. However, existing prediction methods struggle to handle the complex characteristics of meteorological data. To address this challenge, this paper proposes an entropy-driven high-dimensional feature gain XGBoost model. First, traditional meteorological data are transformed into information entropy from an informational perspective, enabling the capture of randomness and nonlinear relationships within the data. Next, an entropy-driven high-dimensional (EDHD) classification feature selection method is designed to identify the relationships between covariates and response variables in the information entropy. Subsequently, a feature-gain XGBoost model is constructed to dynamically determine the optimal splitting features and thresholds, achieving the entropy-driven high-dimensional feature gain XGBoost model (EDHD-FG-XGBoost). Finally, experiments using real wind farm data from the northeastern region of China demonstrate the feasibility and effectiveness of the proposed method.http://dx.doi.org/10.1063/5.0268894
spellingShingle Xing Liu
Xingyu Mou
Ying Zhang
Hui Chen
Xin Wang
Xihao Sun
Chengcheng Wang
Ruixiang Shong
Yunfeng Li
EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and application
AIP Advances
title EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and application
title_full EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and application
title_fullStr EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and application
title_full_unstemmed EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and application
title_short EDHD-FG-XGBoost: Entropy-driven high-dimensional feature gain XGBoost model for short-term wind power prediction and application
title_sort edhd fg xgboost entropy driven high dimensional feature gain xgboost model for short term wind power prediction and application
url http://dx.doi.org/10.1063/5.0268894
work_keys_str_mv AT xingliu edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT xingyumou edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT yingzhang edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT huichen edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT xinwang edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT xihaosun edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT chengchengwang edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT ruixiangshong edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication
AT yunfengli edhdfgxgboostentropydrivenhighdimensionalfeaturegainxgboostmodelforshorttermwindpowerpredictionandapplication