Skip to Main Content
Owing to the intermittency and uncontrollability of wind power, large-scale wind power integrated into power system will bring severe challenges to power system safety operation and power quality. Wind power forecasting technology is one of the key technologies in coping with those problems. It plays an important role on guiding the grid dispatching and production effectively. However, the accuracy of the wind power forecasting may have a direct influence on practical grid operation, especially when the forecasting is lack of NWP (Numerical Weather Prediction) data. Aiming at solving the above troubles, this paper proposes a method of continuous multi-step prediction model based on fuzzy clustering analysis theory. By using this method, continuous prediction result can be achieved which may be ultra-short-term forecast for each 15min interval during 4 hours in future or short-term forecast for each 1h interval during 24 hours in future. At last, an example is presented to valid the effectiveness of this prediction approach.