基于SHAP重要性排序和时空双流的多风场超短期功率预测
Ultra-short-term power forecasting for multiple wind fields based on SHAP importance ranking and spatio-temporal dual flow
付波 1李昊 1权轶 1李超顺 2赵熙临 1杨远程3
作者信息
- 1. 湖北工业大学 电气与电子工程学院, 武汉 430068
- 2. 华中科技大学 土木与水利工程学院, 武汉 430074
- 3. 国网石首市供电公司, 湖北 荆州 434400
- 折叠
摘要
针对多风场风功率预测中时空特征提取不充分的问题,提出一种基于空间、时间双流特征提取的功率预测方法.采用沙普利加性解释(SHAP)方法分析原始高维数值天气预报(NWP)中各变量的重要性,选择贡献度高的变量子集作为预测模型输入,降低模型复杂度.构建基于自适应动态邻接矩阵的改进图注意力网络(IGAT)提取多风场的动态空间特征;同时将多头注意力机制(MHA)与时间卷积网络(TCN)结合,加强关键时序特征的学习.使用前馈神经网络输出多风场功率预测结果.以西北某十风场的数据进行案例研究,结果表明所提模型的预测效果优于其他模型.
Abstract
To address the insufficient spatio-temporal feature extraction in multi-wind field wind power prediction, this paper proposes a power prediction method based on spatial and temporal dual-stream feature extraction.First, the Shapley Additive Explanations ( SHAP) method is employed to analyze the importance of each variable in the original high-dimensional Numerical Weather Prediction ( NWP) , and a subset of variables with high contribution is selected as the input to the prediction model, reducing the complexity of the model.Second, an Improved Graph Attention Network ( IGAT) based on an adaptive dynamic adjacency matrix is built to extract the dynamic spatial features of multiple wind fields.Meanwhile, Multi-Head Attention Mechanism ( MHA) is integrated with Temporal Convolutional Network ( TCN) to enhance the learning of key temporal features.Then, a feed-forward neural network is used to output the power prediction results of multiple wind fields.Finally, a case study is conducted with data from ten wind fields in Northwest China, and our results show the proposed model performs better in prediction than other models.
关键词
多风场功率预测/变量选择/图注意力网络/多头注意力机制/时间卷积网络Key words
multi-wind field power prediction/variable selection/graph attention network/multi-head attention mechanism/temporal convolutional network引用本文复制引用
基金项目
湖北省重点研发计划项目(2021BAA193)
出版年
2024
国家科技期刊平台
NSTL
万方数据