Short-term wind power prediction for wind turbine via kalman filter based on JIT modeling

This paper addresses wind power prediction which is known to be a key technology in EMS(Energy Management Systems). In recent years, an introductory expansion of renewable energy is expected and the prediction of wind power generation is needed for taking in wind power generation. The goal of this work is to predict the amount of generation in the next day from the past actual data and the weather forecast data of wind. In this paper, 24 hours ahead power prediction method using a filtering theory is proposed for wind power generation. The prediction method is a simple algorithm, the procedure of prediction consists of two steps, the data processing and the calculation of predicted values. In the data processing, in order to get the correlative data from the database, we employ JIT(Just-In-Time) Modeling. In the calculation of predicted value, we provide the regression model for wind speed and wind power, and the unknown parameters are estimated via constrained kalman filter. Finally, the advantages of the proposed method over the conventional method are shown through simulations.