A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting

Abstract This paper investigates the multi‐dimensional non‐linear exponential smoothing prediction method under different weight coefficients, so as to realize the short‐term prediction of the original wind power output. Based on the current research on wind power fluctuation prediction, this paper...

Full description

Bibliographic Details
Main Authors: Xidong Zheng, Tao Jin
Format: Article
Language:English
Published: Wiley 2022-12-01
Series:IET Renewable Power Generation
Online Access:https://doi.org/10.1049/rpg2.12395
_version_ 1797986668145278976
author Xidong Zheng
Tao Jin
author_facet Xidong Zheng
Tao Jin
author_sort Xidong Zheng
collection DOAJ
description Abstract This paper investigates the multi‐dimensional non‐linear exponential smoothing prediction method under different weight coefficients, so as to realize the short‐term prediction of the original wind power output. Based on the current research on wind power fluctuation prediction, this paper firstly proposes a new multi‐dimensional nonlinear exponential smoothing prediction method. Based on different weight coefficients, the corresponding short‐term forecast volatility is obtained. Then, the wavelet packet decomposition method is used to further realize the secondary smoothing of the prediction wind power fluctuations. Hybrid energy storage system (HESS) plays an important role in wind power fluctuation suppression from different frequency bands. However, the traditional fixed frequency power allocation method significantly degrades the performance of the accuracy of the algorithm. Therefore, this paper proposes a frequency conversion entropy strategy, which combines energy value with wavelet packet decomposition. By calculating the energy components of different frequency bands, the fluctuation can be divided effectively. Finally, simulation and experiment discussions show that the proposed algorithm in this paper can realize the power allocation effectively compared to the traditional one. And it further verifies the feasibility and reliability of the strategy proposed in this work.
first_indexed 2024-04-11T07:35:36Z
format Article
id doaj.art-cb6eef026b3c48f6828a154e6d69dd6e
institution Directory Open Access Journal
issn 1752-1416
1752-1424
language English
last_indexed 2024-04-11T07:35:36Z
publishDate 2022-12-01
publisher Wiley
record_format Article
series IET Renewable Power Generation
spelling doaj.art-cb6eef026b3c48f6828a154e6d69dd6e2022-12-22T04:36:44ZengWileyIET Renewable Power Generation1752-14161752-14242022-12-0116163573358610.1049/rpg2.12395A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecastingXidong Zheng0Tao Jin1Department of Electrical Engineering Fuzhou University Fuzhou ChinaDepartment of Electrical Engineering Fuzhou University Fuzhou ChinaAbstract This paper investigates the multi‐dimensional non‐linear exponential smoothing prediction method under different weight coefficients, so as to realize the short‐term prediction of the original wind power output. Based on the current research on wind power fluctuation prediction, this paper firstly proposes a new multi‐dimensional nonlinear exponential smoothing prediction method. Based on different weight coefficients, the corresponding short‐term forecast volatility is obtained. Then, the wavelet packet decomposition method is used to further realize the secondary smoothing of the prediction wind power fluctuations. Hybrid energy storage system (HESS) plays an important role in wind power fluctuation suppression from different frequency bands. However, the traditional fixed frequency power allocation method significantly degrades the performance of the accuracy of the algorithm. Therefore, this paper proposes a frequency conversion entropy strategy, which combines energy value with wavelet packet decomposition. By calculating the energy components of different frequency bands, the fluctuation can be divided effectively. Finally, simulation and experiment discussions show that the proposed algorithm in this paper can realize the power allocation effectively compared to the traditional one. And it further verifies the feasibility and reliability of the strategy proposed in this work.https://doi.org/10.1049/rpg2.12395
spellingShingle Xidong Zheng
Tao Jin
A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting
IET Renewable Power Generation
title A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting
title_full A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting
title_fullStr A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting
title_full_unstemmed A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting
title_short A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting
title_sort reliable method of wind power fluctuation smoothing strategy based on multidimensional non linear exponential smoothing short term forecasting
url https://doi.org/10.1049/rpg2.12395
work_keys_str_mv AT xidongzheng areliablemethodofwindpowerfluctuationsmoothingstrategybasedonmultidimensionalnonlinearexponentialsmoothingshorttermforecasting
AT taojin areliablemethodofwindpowerfluctuationsmoothingstrategybasedonmultidimensionalnonlinearexponentialsmoothingshorttermforecasting
AT xidongzheng reliablemethodofwindpowerfluctuationsmoothingstrategybasedonmultidimensionalnonlinearexponentialsmoothingshorttermforecasting
AT taojin reliablemethodofwindpowerfluctuationsmoothingstrategybasedonmultidimensionalnonlinearexponentialsmoothingshorttermforecasting