An improved Grey-based Approach for Short-Term Wind Power Prediction

With the expansion of wind farm installations in most countries all over the world, the power generation has already significantly influenced on the stability and security of the power grid after gridconnection. Wind power forecasting is an effective method for guarantees stability of the power output from wind farm. This paper proposed an improved GM(1,1) based prediction method, and focuses on the wind power online prediction using the relationship between the wind speed and the wind power generation. The simulation results have verified that the developed approach, with GM rolling mechanism, data preprocessing and background value optimizing has better prediction precision over the traditional GM rolling model and data series smoothing model. Finally, utilized a case study at Azuoqi wind farm located in Inner Mongolia province of China, which obviously realized wind power generation prediction for optimizing the wind power control in the wind farm in real time.