《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (2): 652-658.DOI: 10.11772/j.issn.1001-9081.2025030317

• 前沿与综合应用 • 上一篇    

基于贝叶斯优化和特征融合混合模型的短期风电功率预测

付锦程(), 杨仕友   

  1. 浙江大学 电气工程学院,杭州 310027
  • 收稿日期:2025-03-27 修回日期:2025-05-09 接受日期:2025-05-12 发布日期:2025-05-19 出版日期:2026-02-10
  • 通讯作者: 付锦程
  • 作者简介:付锦程(2002—),男,河南开封人,硕士研究生,主要研究方向:风电功率预测、智能优化算法Email:jincheng.fu@zju.edu.cn
    杨仕友(1964—),男,辽宁朝阳人,教授,博士,主要研究方向:智能优化算法、工程电磁场的数值分析与优化设计。

Short-term wind power prediction using hybrid model based on Bayesian optimization and feature fusion

Jincheng FU(), Shiyou YANG   

  1. College of Electrical Engineering,Zhejiang University,Hangzhou Zhejiang 310027,China
  • Received:2025-03-27 Revised:2025-05-09 Accepted:2025-05-12 Online:2025-05-19 Published:2026-02-10
  • Contact: Jincheng FU
  • About author:FU Jincheng, born in 2002, M. S. candidate. His research interests include wind power prediction, intelligent optimization algorithms. Email:jincheng.fu@zju.edu.cn
    YANG Shiyou, born in 1964, Ph. D., professor. His research interests include intelligent optimization algorithms, numerical analysis and optimization design of engineering electromagnetic field.

摘要:

为了提高短期风电功率预测的准确性,提出一种基于贝叶斯优化和特征融合的xLSTM(extended Long Short-Term Memory)-Transformer模型。该模型综合应用长短期记忆(LSTM)网络的时序处理能力和Transformer的自注意力机制的动态特征融合能力。借助贝叶斯优化方法,模型可在较少的迭代次数条件下优化超参数,显著降低模型对计算资源的依赖。实验结果表明,内蒙古某风电场数据集上,与单一的LSTM模型、Transformer模型、门控循环单元(GRU)模型以及未采用贝叶斯优化和特征融合的xLSTM-Transformer模型相比,当步长(LookBack)为4和8时,所提模型的决定系数R2较基准模型平均提升1.2%~11.3%;平均绝对误差(MAE)平均降低12.8%~38.4%;均方根误差(RMSE)平均降低8.6%~35.8%。结果表明,所提模型在短历史输入条件下具有更高的预测精度与稳定性。

关键词: 风电功率预测, 神经网络模型, 贝叶斯优化, 特征融合, 深度学习

Abstract:

To enhance the accuracy of short-term wind power prediction, an xLSTM (extended Long Short-Term Memory)-Transformer model based on Bayesian optimization and feature fusion was proposed. In the proposed model, the temporal processing capability of Long Short-Term Memory (LSTM) network was integrated with the dynamic feature fusion ability of Transformer’s self-attention mechanism. By employing Bayesian optimization method, the hyperparameters of the model were optimized efficiently in a few iterations, thereby reducing the computational resources significantly. The experimental results demonstrate that, on a dataset from a wind farm in Inner Mongolia, when compared with the single LSTM model, Transformer model, Gated Recurrent Unit (GRU) model, and the xLSTM-Transformer model without Bayesian optimization and feature fusion, the proposed model achieves an average increase of 1.2% to 11.3% in the coefficient of determination (R2) compared to the benchmark models when the LookBack are 4 and 8; it also shows an average reduction of 12.8% to 38.4% in the Mean Absolute Error (MAE) and an average reduction of 8.6% to 35.8% in the Root Mean Square Error (RMSE). The results indicate that the proposed model exhibits higher prediction accuracy and stability under conditions of short historical input.

Key words: wind power prediction, neural network model, Bayesian optimization, feature fusion, deep learning

中图分类号: