Combined Wind Speed Prediction Model based on GAT-LSTM
DOI:
https://doi.org/10.6919/ICJE.202409_10(9).0008Keywords:
Wind Speed Prediction; Graph Attention Neural Network; Long Short-Term Memory Network; Combination Model.Abstract
Wind speed has strong volatility, intermittency, and high variability. To predict wind speed, a comprehensive analysis should be conducted based on its temporal and spatial characteristics. This article proposes a combined wind speed prediction model based on graph attention network and long short term memory network (GAT-LSTM), which uses graph structure to describe the spatial correlation of time-series data and establishes a GAT wind field spatial feature model, Introducing attention mechanism to calculate the correlation between nodes in the neighborhood and selectively aggregate weather features of surrounding areas, Input the time series information extracted by GAT network at different time points into LSTM network for wind speed prediction. Based on the wind speed dataset of meteorological observation stations in Denmark and a city in the Netherlands, a comparative analysis was conducted with LSTM model, Multidimensional model, and GCN model. The experimental results showed that the combined wind speed prediction model based on GAT-LSTM had higher prediction accuracy.
Downloads
References
Bo L. Research on Short term Combination Prediction Model of Wind Farm Power Based on Numerical Forecasting[D].Nanjing University of Information Science and Technology, 2014.
Qiuping H,Naxian G,et al.Analysis on Research Progress of Short-term Wind Speed Prediction Model[J].Qinghai Science and Technology,2023,30(06):140-143.
Hsiao Y C , Wu Y C , Lin C .Energy-Efficient Beamforming Design for MU-MISO Mixed RF/VLC Heterogeneous Wireless Networks[J].IEEE Transactions on Signal Processing, 2019, 67(14):3770-3784. DOI:10.1109/TSP.2019.2920612.
Zhuo Z.A Study on Short-Term Wind Energy Prediction AlgorithmBased on Deep Neural Network[D]. Tianjin University,2020.DOI:10.27356.2020.002437.
Wang Y , Zhu C , Zhao J ,et al.Short-Term Time Wind Speed Forecasting Based on Spatio-Temporal Geostatistical Approach and Kriging Method[J].International Journal of Pattern Recognition and Artificial Intelligence, 2021, 35(7).DOI:10.1142/S0218001421590254.
Bolu L,Li W,et al.Multi site wind speed prediction based on graph dynamic attention network[J].Computer Application,1-10[2023-05-04].
Enbo Y ,Guoji X ,Yan H , et al.An efficient short-term wind speed prediction model based on cross-channel data integration and attention mechanisms[J].Energy,2022,256.
Wang Y, Zhang N, Chen X, et al. A Short-Term Residential Load Forecasting Model Based on LSTM Recurrent Neural Network Considering Weather Features[J]. Energies,2021,14(10):2737.
Geng D ,Zhang H ,Wu H .Short-Term Wind Speed Prediction Based on Principal Component Analysis and LSTM[J].Applied Sciences,2020,10(13).
Jingcheng Q ,Mingfang Z ,Yingnan Z , et al.Short-term Wind Speed Prediction with a Two-layer Attention-based LSTM[J].Computer Omputer Systems Science And Engieering,2021,39(2):197-209.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
