基于注意力机制的ABG-GCA模型中长期风电功率预测  

Medium and Long Term Wind Power Prediction by ABG-GCA Model Based on Attention Mechanism

作　　者：蒲海涛 代英健 PU Hai-tao;DAI Ying-jian(College of Electrical Engineering and Automation,Shandong University of Science and Technology,Qingdao 266590,China;Electrical Information Department,Shandong University of Science and Technology-Jinan Campus,Jinan 250031,China)

机构地区：[1]山东科技大学电气与自动化工程学院,山东青岛266590 [2]山东科技大学济南校区电气信息系,山东济南250031

出　　处：《电工电气》2025年第2期10-18,共9页Electrotechnics Electric

基　　金：山东省高等学校本科教学改革研究重点项目(Z2022187&M2023378);山东科技大学教育教学研究“群星计划”项目(QX2022ZD18)。

摘　　要：风电功率预测对电力系统的稳定性和经济性具有重要意义。针对已有模型预测时间较长和预测精度存在较大误差的问题,提出了一种新型的ABG-GCA模型,该模型通过Autoformer的自相关机制与基于全局注意力机制的双向门控循环单元将处理好的数据进行并行预测,对各分量的预测值利用交叉注意力机制来进行权重分配形成高效准确功率的预测结果。实验结果表明,该模型在预测精度和时间效率方面优于传统模型,能够有效捕捉风电功率的变化趋势,对于不同季节的预测自适应性极强且预测精度高。The wind power prediction is of great significance to the stability and economy of power system.In this paper,a new ABGGCA model is proposed to solve the problem that the existing model has a long prediction time and a large error in prediction accuracy.The model uses the autocorrelation mechanism of Autoformer and the bidirectional gated recurrent unit based on the global attention mechanism to predict the processed data in parallel.The cross-attention mechanism is used to assign weights to the predicted values of each component to form an efficient and accurate power prediction result.The experimental results show that the model is superior to the traditional model,in terms of prediction accuracy and time efficiency which can effectively capture the change trend of wind power and prediction for different seasons has strong adaptability and high precision.

关 键 词：风电功率预测 二次分解技术 ABG-GCA模型 中长期预测 自相关机制 全局注意力机制 交叉注意力机制 预测精度 

分 类 号：TM614[电气工程—电力系统及自动化]