A novel time-frequency recurrent network and its advanced version for short-term wind

For the sensible and efficient use of wind energy, accurate wind speed forecast is crucial. To improve the ac-curacy of short-term wind speed prediction, a novel recurrent neural network known as the time-frequency recurrent neural network, or TFR for short, is developed. The wavelet transformation is naturally incorpo-rated into the TFR architecture in order to mine the time-frequency characteristics. Additionally, the convolution processes are combined to extract the inherent correlation of time series, enhancing the TFR's performance and creating an advanced model known as CNN-TFR. The prediction ability, parameter sensitivity, and training time of the suggested models for multi-step wind speed forecasts are examined using the wealth of wind speed data from a genuine observation site. It is found that TFR offers greater prediction performance as compared to conventional recurrent neural networks since it can access frequency domain knowledge. Additionally, CNN-TFR's prediction performance has been further improved, making it superior to other CNN based models. For the proposed CNN-TFR model, its sensitivity to input length and wavelet parameters is investigated. It has been shown that with little training time, the CNN-TFR model with strong and robust prediction ability can be utilized to anticipate real wind speed.

Automated summary

This study develops a novel recurrent neural network model to improve the accuracy of wind speed prediction. By incorporating wavelet transformation and convolution processes, the model demonstrates superior performance in multi-step wind speed forecasts. The model shows low sensitivity to input length and wavelet parameters and is able to accurately predict wind speed in a short amount of time.