A Proposed Forecasting System for Wind Power in Smart Grids

Abstract

The increased level of embedded wind energy generation systems in smart grids posed increased daily challenges because of the intermittent nature of these systems. Forecasting of the generated power from the wind energy systems helps to deal with these challenges. In this paper, a proposed forecasting system for short term wind power prediction is presented. The proposed system is used to increase the accuracy of the forecasted value by creating multiple small datasets with the same features of the main dataset. A neuro-fuzzy model is created for each dataset. The output of each neuro-fuzzy model represents a forecasting of the wind turbine power (WTP). Thereafter, the output of all models is combined using a combination model to calculate the final forecasted WTP.