基于VMD-GRU-EC的短期电力负荷预测方法

Short-term power load forecasting method based on VMD-GRU-EC

为提高负荷预测精度,该文提出一种基于VMD-GRU-EC的短期电力负荷预测方法。针对原始负荷序列非线性和非平稳性的特点,利用VDM分解方法将原始负荷序列分解得到若干个子序列,利用GRU模型分布针对每个子序列建立预测模型,最终将每个子序列的预测值相加得到负荷序列的初始预测值。在得到负荷序列的初始预测之后可得到误差序列,同样利用VMD-GRU模型预测误差序列。利用VMD-GRU模型依次得到初始预测负荷和误差序列后,通过误差校正(error correction,EC)得到最终的预测负荷。实验研究表明,在所有预测模型中,该文所提预测方法预测精度最高,稳定性最强。验证所提模型的有效性与优越性。

To improve the accuracy of load forecasting,this paper proposes a short-term power load forecasting method based on VMD-GRU-EC.In view of the nonlinear and non-stationary characteristics of the original load sequence,the VDM decomposition method is used to decompose the original load sequence to obtain several sub-sequences,and the GRU model distribution is used to establish a prediction model for each sub-sequence,and finally the predicted values of each sub-sequence are added to get The initial predicted value of the load series.After the initial prediction of the load sequence is obtained,the error sequence can be obtained,and the VMD-GRU model is also used to predict the error sequence.After using the VMD-GRU model to obtain the initial predicted load and error sequence in turn,the final predicted load is obtained through error correction(EC).The experimental study shows that among all the prediction models,the prediction method proposed in this paper has the highest prediction accuracy and the strongest stability.The effectiveness and superiority of the proposed model are verified.