A novel combined forecasting model based on neural networks, deep learning approaches, and multi-objective optimization for short-term wind speed forecasting

Jianzhou Wang, Yining An, Zhiwu Li and Haiyan Lu

Energy, 2022, vol. 251, issue C

Abstract: Accurate wind speed prediction has become increasingly important in wind power generation. However, the lack of efficient data preprocessing techniques and integration strategies has been a big obstacle to the development of wind power forecasting system. Therefore, a novel and advanced combined forecasting system comprising a data preprocessing, an integration strategy and several single models is designed in this study. The proposed model not only eliminates the impact of noise, but also integrates several single-model forecasting results through a weight optimization operator. In addition, the uncertain prediction of wind speed is also discussed in detail. The results show that: (a) The MAPE values of the proposed model are 2.8645%, 2.1843% and 2.8727% respectively for the point prediction. (b) The FICP values of the proposed model are 85.1697, 89.5410 and 88.0111 respectively at the significant level α = 0.05 for the uncertainty forecasting. The AWD values are 0.0559, 0.0400 and 0.0361 and the FINAW values are 0.0478, 0.0404 and 0.0390. It is reasonable to conclude that the proposed system can effectively boost the precision and stability of wind speed forecasting and provide a new approach for the exploitation of wind energy.

Keywords: Artificial intelligence; Data preprocessing; Combined forecasting model; Multi-objective optimization (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (8)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222008635
Full text for ScienceDirect subscribers only

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:eee:energy:v:251:y:2022:i:c:s0360544222008635

DOI: 10.1016/j.energy.2022.123960

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().