Multi-Step-Ahead Wind Speed Forecast Method Based on Outlier Correction, Optimized Decomposition, and DLinear Model

Jialin Liu, Chen Gong, Suhua Chen and Nanrun Zhou ()
Additional contact information
Jialin Liu: School of Qianhu, Nanchang University, Nanchang 330031, China
Chen Gong: School of Information Engineering, Nanchang University, Nanchang 330031, China
Suhua Chen: School of Information Engineering, Nanchang University, Nanchang 330031, China
Nanrun Zhou: School of Information Engineering, Nanchang University, Nanchang 330031, China

Mathematics, 2023, vol. 11, issue 12, 1-26

Abstract: Precise and dependable wind speed forecasting (WSF) enables operators of wind turbines to make informed decisions and maximize the use of available wind energy. This study proposes a hybrid WSF model based on outlier correction, heuristic algorithms, signal decomposition methods, and DLinear. Specifically, the hybrid model (HI-IVMD-DLinear) comprises the Hampel identifier (HI), the improved variational mode decomposition (IVMD) optimized by grey wolf optimization (GWO), and DLinear. Firstly, outliers in the wind speed sequence are detected and replaced with the HI to mitigate their impact on prediction accuracy. Next, the HI-processed sequence is decomposed into multiple sub-sequences with the IVMD to mitigate the non-stationarity and fluctuations. Finally, each sub-sequence is predicted by the novel DLinear algorithm individually. The predictions are reconstructed to obtain the final wind speed forecast. The HI-IVMD-DLinear is utilized to predict the real historical wind speed sequences from three regions so as to assess its performance. The experimental results reveal the following findings: (a) HI could enhance prediction accuracy and mitigate the adverse effects of outliers; (b) IVMD demonstrates superior decomposition performance; (c) DLinear has great prediction performance and is suited to WSF; and (d) overall, the HI-IVMD-DLinear exhibits superior precision and stability in one-to-four-step-ahead forecasting, highlighting its vast potential for application.

Keywords: wind speed forecasting; Hampel identifier; improved variational mode decomposition; grey wolf optimization; DLinear (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/12/2746/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/12/2746/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:12:p:2746-:d:1173390

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().