Wind farm cluster power prediction based on graph deviation attention network with learnable graph structure and dynamic error correction during load peak and valley periods

被引:0
|
作者
Yang, Mao [1 ]
Guo, Yunfeng [1 ]
Huang, Tao [2 ]
Fan, Fulin [3 ,4 ]
Ma, Chenglian [1 ]
Fang, Guozhong [5 ]
机构
[1] Northeast Elect Power Univ, Key Lab Modern Power Syst Simulat & Control & Rene, Minist Educ, Jilin 132012, Peoples R China
[2] Politecn Torino, DOE, I-10129 Turin, Italy
[3] Harbin Inst Technol, Sch Elect Engn & Automat, Harbin 150001, Peoples R China
[4] Univ Strathclyde, Inst Energy & Environm, Glasgow G1 1XW, Scotland
[5] State Grid Corp China Northeast Branch, Changchun 130699, Peoples R China
关键词
Load peak and valley characteristics; Improved clustering distance; Learnable GDAN structure; Error dynamic correction; SVMD; Ultra-short-term power prediction; ELECTRICITY;
D O I
10.1016/j.energy.2024.133645
中图分类号
O414.1 [热力学];
学科分类号
摘要
The power prediction accuracy of wind farm cluster (WFC) seriously affects its consumption and the safe and stable operation of power system. The fluctuation of power between wind farms (WFs) significantly affects the wind power ultra-short-term prediction (WPUP) accuracy of WFC. In this regard, this paper proposes a graph deviation attention network (GDAN) considering improved clustering distance and learnable graph structure (LGS) for predicting and correcting the wind power of WFC. And used a weighted distance function combining sequence convergence smoothing effect and correlation to dynamically divide the WFC, and to learn and construct the graph structure. Proposed the GDAN with LGS to mine the convergence correlation of WF subclusters and establish power prediction model. Considering the characteristics of load peak and valley periods (LPVP), introduced a power correction coefficient to reduce the error, and used the successive variational mode decomposition (SVMD) to extract its key components to achieve power prediction and correction. The proposed method is applied to the WFC in Western Inner Mongolia, China. Compared with the comparison model before correction, the RMSE, MAE and MAPE are reduced by 4.27 %, 3.55 % and 17.92 % respectively, and the R2 and Pr are increased by 11.87 % and 9.88 % respectively.
引用
收藏
页数:26
相关论文
共 15 条
  • [11] Dynamic spatio-temporal correlation and hierarchical directed graph structure based ultra-short-term wind farm cluster power forecasting method
    Wang, Fei
    Chen, Peng
    Zhen, Zhao
    Yin, Rui
    Cao, Chunmei
    Zhang, Yagang
    Duic, Neven
    APPLIED ENERGY, 2022, 323
  • [12] Adaptive Feature Selection and GCN With Optimal Graph Structure-Based Ultra-Short-Term Wind Farm Cluster Power Forecasting Method
    Xu, Honglai
    Zhang, Yiran
    Zhen, Zhao
    Xu, Fei
    Wang, Fei
    IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2024, 60 (01) : 1804 - 1813
  • [13] M2GSNet: Multi-Modal Multi-Task Graph Spatiotemporal Network for Ultra-Short-Term Wind Farm Cluster Power Prediction
    Fan, Hang
    Zhang, Xuemin
    Mei, Shengwei
    Chen, Kunjin
    Chen, Xinyang
    APPLIED SCIENCES-BASEL, 2020, 10 (21): : 1 - 15
  • [14] Short-term wind farm cluster power point-interval prediction based on graph spatio-temporal features and S-Stacking combined reconstruction
    Hou, Xinxing
    Hu, Wenbo
    Luo, Maomao
    HELIYON, 2024, 10 (14)
  • [15] A D-stacking dual-fusion, spatio-temporal graph deep neural network based on a multi-integrated overlay for short-term wind-farm cluster power multi-step prediction
    Qu, Zhijian
    Li, Jian
    Hou, Xinxing
    Gui, Jianglin
    ENERGY, 2023, 281