AUTHOR=Chen Wenjin , Qi Weiwen , Li Yu , Zhang Jun , Zhu Feng , Xie Dong , Ru Wei , Luo Gang , Song Meiya , Tang Fei 

TITLE=Ultra-Short-Term Wind Power Prediction Based on Bidirectional Gated Recurrent Unit and Transfer Learning

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.808116

DOI=10.3389/fenrg.2021.808116

ISSN=2296-598X

ABSTRACT=The wind power forecasting (WPF) is imperative to the control and dispatch of power grid. Firstly, an ultra-short-term prediction method based on multilayer bidirectional gated recurrent unit (Bi-GRU) and fully connected (FC) layer is proposed. The layers of Bi-GRU extract the temporal feature information of wind power and meteorological data, and the FC layer predicts wind power by changing dimension to match output vector. Furthermore, a transfer learning (TL) strategy is utilized to establish prediction model of target wind farm with fewer data and less training time based on source wind farm. The proposed method is validated on two wind farms located in China and the results proves its superior prediction performance compared with other approaches.