基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测

付桐林

doi:doi:10.19912/j.0254-0096.tynxb.2024-0194

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测

更新时间：2025-12-02

- 基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测
- 基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测
- 太阳能学报 2025年46卷第6期页码：659-666
- 作者机构：
- 作者简介：
- 基金信息：
  
  国家社会科学基金（18XTJ003）;甘肃省教育厅科技创新项目（2023B-211）;陇东学院博士基金（XYBYZK2305）;庆阳市科技计划项目（QY-STK-2023B-119）
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-0194
  中图分类号： TM614
- 网络出版：2025-07-07，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
付桐林. 基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测[J]. 太阳能学报, 2025,46(6):659-666.

付桐林. 基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测[J]. 2025, 46(6): 659-666.
付桐林. 基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测[J]. 太阳能学报, 2025,46(6):659-666. DOI： doi:10.19912/j.0254-0096.tynxb.2024-0194.

付桐林. 基于机器学习耦合启发式算法和数据预处理的无负约束组合风速预测[J]. 2025, 46(6): 659-666. DOI： doi:10.19912/j.0254-0096.tynxb.2024-0194.

摘要

首先将人工神经网络（ANN）、支持向量机（SVM）及极值学习机（ELM）与集合经验模态分解（EEMD）和灰狼算法（GWO）相耦合

构建多个混合模型对中国黄土高原陇东区环县风电场风速进行预测

进而将各混合模型的预测结果作为输入变量

以预测误差平方和最小为目标函数

构建无负约束的组合模型NNCT

并采用灰狼算法优化组合模型的权重

实现研究区域风电场风速的准确预测。数值结果表明

该模型可有效降低模型选择的风险

具有更高的预测精度。

Abstract

In this study

three machine learning models

including artificial neural network （ANN）

support vector machine （SVM）

and extreme learning machine （ELM）

were coupled with ensemble empirical mode decomposition （EEMD） and Grey wolf algorithm （GWO） to construct hybrid models to predict wind speed of Huan County wind farm in Longdong area of Loess Plateau in China. And then the forecasting results of each hybrid model were taken as input variables

and the minimum sum of squares of prediction errors was regarded as the objective function

the combined model without negative constraint theory （NNCT） was proposed to realize the accurate prediction of wind speed in the study area

while the weight of the combined model was optimized by using GWO algorithm. Numerical simulation results show that the GWO-NNCT model can effectively reduce the risk of model selection and has higher prediction accuracy than that of the hybrid models and single machine learning model.

关键词

Keywords

references

WANG J Z, SONG Y L, LIU F, et al.Analysis and application of forecasting models in wind power integration: a review of multi-step-ahead wind speed forecasting models[J]. Renewable and sustainable energy reviews, 2016, 60: 960-981.

SHUKUR O B, LEE M H.Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA[J]. Renewable energy, 2015, 76: 637-647.

SU Z Y, WANG J Z, LU H Y, et al.A new hybrid model optimized by an intelligent optimization algorithm for wind speed forecasting[J]. Energy conversion and management, 2014, 85: 443-452.

ZHANG S H, WANG C, LIAO P, et al.Wind speed forecasting based on model selection, fuzzy cluster, and multi-objective algorithm and wind energy simulation by Betz's theory[J]. Expert systems with applications, 2022, 193: 116509.

WANG C, ZHANG S H, LIAO P, et al.Wind speed forecasting based on hybrid model with model selection and wind energy conversion[J]. Renewable energy, 2022, 196: 763-781.

FAMOSO F, BRUSCA S, D'URSO D, et al. A novel hybrid model for the estimation of energy conversion in a wind farm combining wake effects and stochastic dependability[J]. Applied energy, 2020, 280: 115967.

AASIM, SINGH S N, MOHAPATRA A. Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting[J]. Renewable energy, 2019, 136: 758-768.

LEUENBERGER M, KANEVSKI M.Extreme learning machines for spatial environmental data[J]. Computers & geosciences, 2015, 85: 64-73.

JIANG P, MA X J.A hybrid forecasting approach applied in the electrical power system based on data preprocessing, optimization and artificial intelligence algorithms[J]. Applied mathematical modelling, 2016, 40(23/24): 10631-10649.

FU W L, WANG K, LI C S, et al.Multi-step short-term wind speed forecasting approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA optimization and ELM[J]. Energy conversion and management, 2019, 187: 356-377.

CHEN Y, ZHANG S, ZHANG W Y, et al.Multifactor spatio-temporal correlation model based on a combination of convolutional neural network and long short-term memory neural network for wind speed forecasting[J]. Energy conversion and management, 2019, 185: 783-799.

JASEENA K U, KOVOOR B C.Decomposition-based hybrid wind speed forecasting model using deep bidirectional LSTM networks[J]. Energy conversion and management, 2021, 234: 113944.

FU T L, LI X R.Hybrid the long short-term memory with whale optimization algorithm and variational mode decomposition for monthly evapotranspiration estimation[J]. Scientific reports, 2022, 12: 20717.

HUANG N E, SHEN Z, LONG S R, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London series A, 1998, 454(1971): 903-998.

XIAO L, WANG J Z, DONG Y, et al.Combined forecasting models for wind energy forecasting: a case study in China[J]. Renewable and sustainable energy reviews, 2015, 44: 271-288.

CHENG Z S, WANG J Y.A new combined model based on multi-objective salp swarm optimization for wind speed forecasting[J]. Applied soft computing, 2020, 92: 106294.

LIU Z K, JIANG P, ZHANG L F, et al.A combined forecasting model for time series: application to short-term wind speed forecasting[J]. Applied energy, 2020, 259: 114137.

FU T L, ZHANG S H.Wind speed forecast based on combined theory, multi-objective optimisation, and sub-model selection[J]. Soft computing, 2022, 26(24): 13615-13638.

MIRJALILI S, MIRJALILI S M, LEWIS A.Grey wolf optimizer[J]. Advances in engineering software, 2014, 69: 46-61.

FU T L, WANG C.A novel ensemble wind speed forecasting model in the Longdong area of Loess Plateau in China[J]. Mathematical problems in engineering, 2018, 2018: 2506157.

高桂革, 原阔, 曾宪文, 等. 基于改进CEEMD-CS-ELM的短期风速预测[J]. 太阳能学报, 2021, 42(7): 284-289.

张金良, 刘子毅, 孙安黎. 计及误差信息的自适应超短期风速预测模型[J]. 太阳能学报, 2024, 45(3): 18-28.

邱文智, 张文煜, 郭振海, 等. 基于二次分解和乌鸦搜索算法优化组合模型的超短期风速预测[J]. 太阳能学报, 2024, 45(3): 73-82.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于样本熵双分解和SSA-LSTM的超短期风速预测

利用混合深度学习算法的时空风速预测

基于MATLAB系统辨识工具箱的风信号预测

基于CEEMDAN二次分解和LSTM的风速多步预测研究