基于ARIMA-双向GRU混合模型的风电功率点值预测

Point Value Prediction of Wind Power Based on ARIMA-Bidirectional GRU Hybrid Model

为了提高风电预测的有效性,本文探讨了一种自回归积分滑动平均模型–双向门控循环单元(ARIMA-双向GRU)混合模型用于预测未来风电功率。本研究使用的数据集来自某内陆风电场的一台风机,包含一年的逐小时风速和功率数据。对比了该混合模型与单独使用ARIMA、GRU及其他混合模型的预测效果,以评估所提方法的有效性。实验结果表明,ARIMA-双向GRU混合模型在多个评估指标上表现优于单一的统计模型和深度学习模型,具有更高的预测准确性和稳定性。In order to improve the efficiency of wind power forecasting, this paper discusses an autoregressive integrated moving average model and bidirectional gated cycle unit (ARIMA-Bidirectional GRU) hybrid model for predicting future wind power. The data set used in this study is from a wind turbine at an inland wind farm and contains a year’s worth of hourly wind speed and power data. The prediction effect of the proposed model was compared with that of ARIMA, GRU and other hybrid models alone to evaluate the effectiveness of the proposed method. The experimental results show that the ARMIA-Bidirectional GRU hybrid model outperforms the single statistical model and the deep learning model on multiple evaluation indicators, and has higher prediction accuracy and stability.