A novel wind speed prediction strategy based on Bi-LSTM, MOOFADA and transfer learning for centralized control centers

Tao Liang, Qing Zhao, Qingzhao Lv and Hexu Sun

Energy, 2021, vol. 230, issue C

Abstract: With the rapid development of wind power generation, a centralized monitoring center for wind farms has emerged to save investment and reduce operating costs. However, it is a daunting challenge for the intelligent wind speed prediction system of centralized control center to realize the wind speed prediction of wind farms in different environments. To this end, this paper proposes a multi-wind farm wind speed prediction strategy suitable for wind farm centralized control center. Firstly, the Bi-LSTM deep learning model is pre-trained with the historical data of four wind farms in typical geographical locations to obtain four intelligent wind speed prediction models with different characteristic parameters. Then, transfer learning is used to transfer the four pre-trained models to the wind farm centralized control center, and the wind speed of any wind farm can be predicted using these four Bi-LSTM models. Finally, the MOOFADA optimization algorithm is used to weight the four sets of prediction results to obtain the optimal wind speed prediction results. Experiments and comparisons with a variety of algorithms show that this algorithm is far higher in prediction accuracy than other algorithms, and has strong adaptability, which can be widely used in wind speed prediction for wind farms.

Keywords: Wind speed prediction; VMD; Bi-LSTM; Transfer learning; MOOFADA (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (26)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S036054422101152X
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:230:y:2021:i:c:s036054422101152x

DOI: 10.1016/j.energy.2021.120904

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 ().