Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm
The input features of existing wind power time-series data prediction models are difficult to indicate the potential relationships between data, and the prediction methods are based on deep learning, which makes the convergence of the models slow and difficult to be applied to the actual production...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-06-01
|
Series: | Heliyon |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023041452 |
_version_ | 1797808410166558720 |
---|---|
author | Shijie Guan Yongsheng Wang Limin Liu Jing Gao Zhiwei Xu Sijia Kan |
author_facet | Shijie Guan Yongsheng Wang Limin Liu Jing Gao Zhiwei Xu Sijia Kan |
author_sort | Shijie Guan |
collection | DOAJ |
description | The input features of existing wind power time-series data prediction models are difficult to indicate the potential relationships between data, and the prediction methods are based on deep learning, which makes the convergence of the models slow and difficult to be applied to the actual production environment. To solve the above problems, an ultra-short-term wind power prediction model based on the XGBoost algorithm combined with financial technical index feature engineering and variational ant colony algorithm is proposed. The model innovatively applies financial technical indicators from financial time series data to wind power time series data and creates a class of model input features that can highly condense the potential relationships between time series data. A bionic algorithm is used to search for the best computational parameters for financial technical indicators to reduce the reliance on financial experts' experience. Taking the German power company Tennet wind power data set as an example, the prediction model proposed in this study has an mean absolute error of 0.859 and a root mean square error of 1.329, and it takes only 244 ms to complete the prediction. Thus, this study provides a new solution for ultra-short-term wind power prediction. |
first_indexed | 2024-03-13T06:37:03Z |
format | Article |
id | doaj.art-739ac41f2cbc48a2a4fbc11bc20953c0 |
institution | Directory Open Access Journal |
issn | 2405-8440 |
language | English |
last_indexed | 2024-03-13T06:37:03Z |
publishDate | 2023-06-01 |
publisher | Elsevier |
record_format | Article |
series | Heliyon |
spelling | doaj.art-739ac41f2cbc48a2a4fbc11bc20953c02023-06-09T04:28:38ZengElsevierHeliyon2405-84402023-06-0196e16938Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithmShijie Guan0Yongsheng Wang1Limin Liu2Jing Gao3Zhiwei Xu4Sijia Kan5School of Data Science and Application, Inner Mongolia University of Technology, Hohhot 010080, China; Software Service Engineering Technology Research Center, Inner Mongolia Autonomous Region, Hohhot 010080, ChinaSchool of Data Science and Application, Inner Mongolia University of Technology, Hohhot 010080, China; Software Service Engineering Technology Research Center, Inner Mongolia Autonomous Region, Hohhot 010080, China; Corresponding author. School of Data Science and Application, Inner Mongolia University of Technology, Hohhot 010080, China.School of Data Science and Application, Inner Mongolia University of Technology, Hohhot 010080, China; Software Service Engineering Technology Research Center, Inner Mongolia Autonomous Region, Hohhot 010080, ChinaSchool of Computer and Information, Inner Mongolia Agricultural University, Hohhot 010018, ChinaSchool of Data Science and Application, Inner Mongolia University of Technology, Hohhot 010080, China; Software Service Engineering Technology Research Center, Inner Mongolia Autonomous Region, Hohhot 010080, ChinaSchool of Natural Sciences, The University of Manchester, Manchester, M13 9PL, UKThe input features of existing wind power time-series data prediction models are difficult to indicate the potential relationships between data, and the prediction methods are based on deep learning, which makes the convergence of the models slow and difficult to be applied to the actual production environment. To solve the above problems, an ultra-short-term wind power prediction model based on the XGBoost algorithm combined with financial technical index feature engineering and variational ant colony algorithm is proposed. The model innovatively applies financial technical indicators from financial time series data to wind power time series data and creates a class of model input features that can highly condense the potential relationships between time series data. A bionic algorithm is used to search for the best computational parameters for financial technical indicators to reduce the reliance on financial experts' experience. Taking the German power company Tennet wind power data set as an example, the prediction model proposed in this study has an mean absolute error of 0.859 and a root mean square error of 1.329, and it takes only 244 ms to complete the prediction. Thus, this study provides a new solution for ultra-short-term wind power prediction.http://www.sciencedirect.com/science/article/pii/S2405844023041452Industrial applications of financial technical indicatorsGradient boosting regression treesParameter optimization theoryWind power prediction |
spellingShingle | Shijie Guan Yongsheng Wang Limin Liu Jing Gao Zhiwei Xu Sijia Kan Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm Heliyon Industrial applications of financial technical indicators Gradient boosting regression trees Parameter optimization theory Wind power prediction |
title | Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm |
title_full | Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm |
title_fullStr | Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm |
title_full_unstemmed | Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm |
title_short | Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm |
title_sort | ultra short term wind power prediction method combining financial technology feature engineering and xgboost algorithm |
topic | Industrial applications of financial technical indicators Gradient boosting regression trees Parameter optimization theory Wind power prediction |
url | http://www.sciencedirect.com/science/article/pii/S2405844023041452 |
work_keys_str_mv | AT shijieguan ultrashorttermwindpowerpredictionmethodcombiningfinancialtechnologyfeatureengineeringandxgboostalgorithm AT yongshengwang ultrashorttermwindpowerpredictionmethodcombiningfinancialtechnologyfeatureengineeringandxgboostalgorithm AT liminliu ultrashorttermwindpowerpredictionmethodcombiningfinancialtechnologyfeatureengineeringandxgboostalgorithm AT jinggao ultrashorttermwindpowerpredictionmethodcombiningfinancialtechnologyfeatureengineeringandxgboostalgorithm AT zhiweixu ultrashorttermwindpowerpredictionmethodcombiningfinancialtechnologyfeatureengineeringandxgboostalgorithm AT sijiakan ultrashorttermwindpowerpredictionmethodcombiningfinancialtechnologyfeatureengineeringandxgboostalgorithm |