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

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