基于CEEMDAN-BO-LSTNet的风电出力短期预测

为提高风电出力预测精度，提出一种自适应噪声完备集合经验模态分解(CEEMDAN)-贝叶斯优化(BO)-长短期时序网络(LSTNet)对风电机组输出功率进行短期预测。清洗数据，采用CEEMDAN对清洗后的原始功率数据进行分解，得到若干个子序列；将分解得到的子序列输入至LSTNet模型，通过对LSTNet的超参数使用BO算法优化，输出子序列的预测结果；将各序列的预测结果进行叠加重构得到最终预测结果。通过对渭南某风电场机组实测数据进行实例仿真，设置消融分析和对比分析，结果表明文中所提方法相较于其他模型，预测精度得到有效提升。

Short-term forecasting of wind power output based on CEEMDAN-BO-LSTNet

In order to improve the prediction accuracy of wind power output, an adaptive noise-complete ensemble empirical mode decomposition (CEEMDAN) -Bayesian optimization (BO) -long and short time series network (LSTNet) was proposed to predict the output power of wind turbines in the short term. Firstly, the data were cleaned, and then CEEMDAN was used to decompose the original power data after cleaning, and several sub-sequences were obtained. Input the decomposed subsequences into the LSTNet model, optimize the LSTNet hyperparameters by using BO algorithm, and output the prediction results of the subsequences. Finally, the prediction results of each sequence were superimposed and reconstructed to obtain the final prediction results. Through the example simulation of the measured data of a wind farm unit in Weinan, ablation analysis and comparative analysis were set up. The results show that compared with other models, the prediction accuracy of the proposed method is effectively improved.