Multi-source deep transfer learning with stacked denoising autoencoder and Wasserstein distance for wind power prediction in new wind farm

•Overcome the challenge of insufficient historical data in newly established wind farms.•Stacked denoising autoencoder is used to establish feature correlations between the source and target domain.•The parameters of LSTM prediction model from a source wind farm are transferred to the target farm’s...

Full description

Bibliographic Details

Published in:	Measurement : journal of the International Measurement Confederation Vol. 258; p. 119225
Main Authors:	Xu, Haiyan, Hao, Wenguang, Zhao, Yong, Tian, Hongda
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 30.01.2026
Subjects:	Stacked denoising autoencoder Transfer learning Wasserstein distance Wind power forecasting Wasserstein distance Wind power forecasting Transfer learning Stacked denoising autoencoder
ISSN:	0263-2241
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!