Short-term wind power predictions for the Romanian electric power system

In the recent years, the wind power installed into power systems has grown at a high rate. In order to maintain the safe operation of these systems, the need for wind power forecasting models had become more pregnant. In the present work a series of tests were performed using the recorded values of power generated by wind power plants at the level of entire Romanian power system. As prediction model, a fuzzy inference system based on a clustering technique was used. The results showed that the proposed method has a great potential but needs to integrate some explanatory variables in order to provide better accuracies.