WIND POWER PREDICTION BASED ON DEEP LEARNING METHOD AND ITS UNCERTAINTY

As a type of clean and renewable energy source, wind power is being widely used all around the world. However, owing to the uncertainty and instability of the wind power, it is essential to build an accurate prediction model for wind power. In order to build the model, the hidden rules of wind power patterns are extracted by historical data from wind farm based on deep belief network (DBN) and a power-law model of turbulence intensity is also proposed. Several experiments are conducted to compare different solutions to DBN. The experimental results show that prediction errors are significantly reduced using the proposed technique. Depth learning theory has a strong scientific and engineering practical value in the field of wind power prediction with upper and lower boundary. It is easy for dispatch to make plan and avoid waste.