A novel spatio-temporal wind speed forecasting method based on the microscale meteorological model and a hybrid deep learning model

Dongqin Zhang, Gang Hu, Jie Song, Huanxiang Gao, Hehe Ren and Wenli Chen

Energy, 2024, vol. 288, issue C

Abstract: Wind power, as a renewable alternative to conventional fossil fuel energy sources, exhibits substantial variability owing to fluctuations in wind velocity. In light of this, the present study puts forward a novel approach for spatio-temporal wind speed forecasting. It enables the prediction of multi-step ahead wind speeds at any location within a given region utilizing data from a single anemometer. The hybrid deep learning model and microscale meteorological model are employed to carry out the temporal and spatial wind speed forecasting, respectively. Specifically, we implement an enhanced complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) technique for signal decomposition to improve time series prediction accuracy, followed by prediction of subsequences via the hybrid deep learning model. In addition, instantaneous wind speed is divided into mean and fluctuating components, and they are then predicted by using the wind speed ratios, wind direction variations and correlation relationships between the observation location and the prediction site, obtained by the microscale meteorological model. Finally, the accuracy and reliability of the proposed model are validated against observational data. This innovative approach generates accurate wind speed forecasting in both temporal and spatial domains.

Keywords: Spatio-temporal wind speed forecasting; Nonstationary transformer; Long short-term memory; Temporal convolution network; Microscale meteorological model (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223032176
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:288:y:2024:i:c:s0360544223032176

DOI: 10.1016/j.energy.2023.129823

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 ().