A Combined Model Based on Secondary Decomposition and Long Short-Term Memory Networks for Enhancing Wind Power Forecast

Abstract

Accurately predicting the potential wind power generation is of paramount importance in advancing the contribution of wind energy within the overall energy production landscape. To reduce dependence on fossil fuels, there is an urgent need to accelerate the integration of renewable energy sources, such as wind power. Moreover, ensuring a stable equilibrium between energy supply and demand hinges upon a profound understanding of the anticipated energy generation capacity. This paper presents a short-term forecasting model using data from the West of Duddon Sands, Barrow, and Horns Power sites. In pursuit of this goal, we have meticulously developed hybrid prediction models based on long short-term memory (LSTM) and bi-directional LSTM (Bi-LSTM) architectures. These models entail an initial data decomposition stage followed by the prediction phase. While some models solely incorporate the empirical mode decomposition (EMD) method for decomposition, others combine EMD with wavelet decomposition (WD) and swarm decomposition (SWD) for a more comprehensive approach. This investigation encompasses a range of models, including EMD-LSTM, EMD-WD-LSTM, EMD-SWD-LSTM, Bi-LSTM, EMD-Bi-LSTM, EMD-WD-Bi-LSTM, and EMD-SWD-Bi-LSTM. After a meticulous analysis of the outcomes generated by each model, a consistent trend emerges: the EMD-SWD-LSTM model consistently yields elevated R(2 )values, signifying a heightened level of predictive accuracy and success.