.png){kind=icon}
返回
Time-variant post-processing method for long-term numerical wind speed forecasts based on multi-region recurrent graph network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.energy.2022.125021.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Weather Research and Forecasting (WRF) is widely used for long-term wind speed prediction. To reduce the inherent systematic error of the WRF, a graph-based wind speed prediction model is proposed by post-processing the WRF. The proposed model contains four stages. In stage 1, the WRF model is applied to generate raw wind speed prediction results. In stage 2, Planar Maximally Filtered Graph (PMFG) is used to construct an informative graph of the wind field. In stage 3, Deep Autoencoder-like Nonnegative Matrix Factorization (DANMF) and Subgraph Alignment and Region Organization (SARO) are utilized to divide the graph into several regions. In stage 4, Multi-region Recurrent Graph Network (MRGN) model is proposed to build multiple regional models, aggregate them via time-variant ensemble weights, and generate improved long-term wind speed prediction results. The wind speed prediction results on 25 real meteorological monitoring nodes show that: (1) the proposed model outperforms WRF and 3 state-of-the-art models with a 95% confidence level; (2) the proposed model tends to produce better performance in strongly dynamic wind speed; (3) the proposed model has enough computational efficiency for practice. In conclusion, the proposed model is effective to improve WRF performance and has application potential.
Keyword:
Weather research and forecasting
Wind speed
Long-term forecasting
Statistical post -processing
Graph neural network
Time -variant prediction
期刊
IF:
9.4
论文数:
4.3W
被引数:
20.2W
机构
引用论文
Wind speed big data forecasting using time-variant multi-resolution ensemble model with clustering auto-encoder.png)
APPLIED ENERGY
APPLIED ENERGYIF11
PREAI
分享收藏Spatio-Temporal Graph Deep Neural Network for Short-Term Wind Speed Forecasting用于短期风速预测的时空图深度神经网络
PREAI
分享收藏
Stochastic multi-objective optimal energy management of grid-connected unbalanced microgrids with renewable energy generation and plug-in electric vehicles含可再生能源发电和插电式电动汽车的并网不平衡微电网随机多目标优化能量管理ENERGY
ENERGYIF9.4
PREAI
分享收藏Model predictive control for load frequency of hybrid power system with wind power and thermal power风电与火电混合电力系统负荷频率的模型预测控制ENERGY
ENERGYIF9.4
PREAI
分享收藏
查看更多内容