Research on A Forecasting Model of Wind Power based on Recurrent Neural Network with Long Short-term Memory
- Resource Type
- Conference
- Authors
- Li, Anying; Cheng, Lei
- Source
- 2019 22nd International Conference on Electrical Machines and Systems (ICEMS) Electrical Machines and Systems (ICEMS), 2019 22nd International Conference on. :1-4 Aug, 2019
- Subject
- Power, Energy and Industry Applications
Predictive models
Wind power generation
Training
Forecasting
Recurrent neural networks
Logic gates
Data models
wind power forecasting
recurrent neural network (RNN)
long short-term memory (LSTM)
- Language
- ISSN
- 2642-5513
The forecasting of the wind power, which is very important for the stability and reliability of the grid, is challenge for the uncertainty and randomness of the wind power. This paper proposed a forecasting model of wind power based on recurrent neural network (RNN) with long short-term memory (LSTM). With the help of the sequence-dependence characteristic of RNN, the proposed model can be trained by smaller data sets but achieve more accurate forecast of wind power. LSTM is involved into the model to improve the oblivion and avoid gradient disappearance. The experimental results verify the effectiveness of the proposed forecasting model.