Short-term wind power forecasting based on SSA-VMD-LSTM

Abstract

Wind power forecasting plays a key role in balancing the power supply and load demand of the system. To achieve reasonable processing and decomposition of input data for power prediction, a combined forecasting model is proposed, in which Sparrow Search Algorithm (SSA) is adopted to optimize Variational Mode Decomposition (VMD) parameters to solve the problem that VMD is difficult to achieve optimal decomposition by manually setting parameters. Firstly, the SSA is used to optimize the VMD parameters, and then the optimized VMD is used to decompose the data. At the same time, the entropy weight-grey relational analysis method is used to analyze the correlation of environmental variables, and the combination of the most relevant influencing factors and the decomposed modal components is selected as the input of the LSTM prediction model to obtain more accurate prediction results. The example results show that the SSA-VMD-LSTM method can effectively improve the prediction accuracy and reduce the wind power prediction error compared with other methods, which verifies the effectiveness of the prediction model.

Keywords

• Wind power forecasting
• Sparrow search algorithm
• Variational mode decomposition
• Entropy weight method
• Grey relational analysis
• Combined prediction mode