Abstract
To protect the environment and achieve the Sustainable Development Goals (SDGs), reducing greenhouse gas emissions has been actively promoted by global governments. Thus, clean energy, such as wind power, has become a very important topic among global governments. However, accurately forecasting wind power output is not a straightforward task. The present study attempts to develop a fuzzy seasonal long short-term memory network (FSLSTM) that includes the fuzzy decomposition method and long short-term memory network (LSTM) to forecast a monthly wind power output dataset. LSTM technology has been successfully applied to forecasting problems, especially time series problems. This study first adopts the fuzzy seasonal index into the fuzzy LSTM model, which effectively extends the traditional LSTM technology. The FSLSTM, LSTM, autoregressive integrated moving average (ARIMA), generalized regression neural network (GRNN), back propagation neural network (BPNN), least square support vector regression (LSSVR), and seasonal autoregressive integrated moving average (SARIMA) models are then used to forecast monthly wind power output datasets in Taiwan. The empirical results indicate that FSLSTM can obtain better performance in terms of forecasting accuracy than the other methods. Therefore, FSLSTM can efficiently provide credible prediction values for Taiwan’s wind power output datasets.
Highlights
The results indicated that the hybrid models wavelet transform (WT)-recurrent neural network (RNN)-support vector machine (SVM), WT-long short-term memory network (LSTM)-SVM, and WT-gated recurrent units network (GRU)-SVM obtained the best performance
LSTM models have been successfully used in time series forecasting problems
This study developed a novel fuzzy seasonal long short-term memory network (FSLSTM) model to exploit the unique strength of the fuzzy seasonal index and the LSTM technique in order to predict wind power output in Taiwan
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Yu et al [3] developed hybrid models that combine the wavelet transform (WT) with the support vector machine (SVM), gated recurrent units network (GRU), standard recurrent neural network (RNN), and LSTM models for wind-speed forecasting. Liu et al [5] used combined wavelet packet decomposition with a convolutional neural network and convolutional long shortterm memory network to forecast one-day wind speed. The long short-term memory model was developed on the basis of recurrent neural networks and is of a cyclical type. The long short-term memory model retains the advantages of the recurrent neural network but is able to handle short-term dependencies. Shahid et al [21] developed a novel genetic long short-term memory (GLSTM) method; this method improved wind power predictions from 6% to 30% compared to existing techniques.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
