A deep reinforcement learning approach for wind speed forecasting

The conventional wind forecasting methods often struggle to handle the non-stationary and incon-sistent wind patterns. This paper presents a hybrid method of Empirical Wavelet Transform (EWT)and Deep Reinforcement Learning (DRL) for wind speed modeling to overcome the forecasting chal-lenges. The EWT method transforms the original wind speed series into several independent modesand a residual series. In addition, the DRL method is utilised to optimise the weights associated withthree distinct supervised deep learning models, i.e., Long Short-Term Memory (LSTM), ConvolutionalNeural Networks with LSTM (CNN-LSTM), and CNN with Gated Recurrent Units (CNN-GRU). The per-formance of the proposed EWT-DRL is evaluated against deep learning models, including LSTM,CNN-LSTM, CNN-GRU, and their coupling with EWT. The combination of EWT and the DRL (EWT-DRL)method achieves a Mean Absolute Error (MAE) of 0.151, a Mean Squared Error (MSE) of 0.060, a RootMean Squared Error (RMSE) of 0.192, and a correlation coefficient (R) of 0.9913. These results indicatethe effectiveness of EWT-DRL in improving accuracy for wind speed modeling.