为提高多输入特征下光伏发电功率模型的短期预测精度，提出了一种基于优化时域卷积网络超参数的光伏功率预测组合模型（LGGWO-TCN-MHSA）。该模型集改进灰狼优化算法（levy gold gray wolf optimization, LGGWO）、时域卷积网络（temporal convolutional network, TCN）和多头自注意力机制（malti-head self-attention, MHSA）于一体。首先，采用斯皮尔曼相关系数法提取对光伏功率影响较大的主要特征，并输入至TCN预测模型；然后，将提出的多策略改进灰狼优化算法LGGWO应用于TCN内部进行超参数优化，改善模型预测性能；最后，将预测值输入至多头自注意力模型中进一步提升预测精度。实验采用澳大利亚原始光伏数据进行验证，通过与卷积神经网络（convolutional neural networks, CNN）、长短期记忆神经网络（long short-term memory, LSTM）等六组模型进行对比，所提模型在测试数据集上的平均绝对误差（mean absolute error, MAE）和均方根误差（root mean square error, RMSE）分别降低了2.03%~82.0%和10.5%~80.1%，结果表明：所提方法具有较高的预测精度和良好的稳定性。

To improve the short-term prediction accuracy of photovoltaic power generation models with multiple input features, a photovoltaic power prediction ensemble model LGGWO-TCN-MHSA based on optimizing TCN hyperparameters was proposed. The model integrated the levy gold grey wolf optimization (LGGWO), temporal convolutional network (TCN), and multi-head self-attention mechanism (MHSA). First, the Spearman correlation coefficient method extracted the main features that significantly affect photovoltaic power, which were then fed into the TCN prediction model. Then, the proposed multi-strategy LGGWO was applied to the TCN for hyperparameter optimization, which improved the model's prediction performance. Finally, the predicted values were input into the multi-head self-attention model to further boost prediction accuracy. The experiment was verified using original Australian photovoltaic data. By comparing with six groups of models including convolutional neural networks (CNN) and long short-term memory neural networks (LSTM), the mean absolute error (MAE) and root mean square error (RMSE) of the proposed model on the test data set were reduced by 2.03% ~ 82.0% and 10.5% ~ 80.1%, respectively. The results show that the proposed method has high prediction accuracy and good stability.