Hour-ahead wind power and speed forecasting using market basket analysis and radial basis function network

Wind power is one of the most rapidly growing renewable energies for power generation nowadays. However, operation of power systems becomes challenging due to intermittent characteristics from wind energies. Consequently, effective wind power forecasting is crucial because of the economic consideration and operation. This paper presents a novel technique for short-term wind power and wind speed forecasting (1 hour ahead) by using market basket analysis (MBA) and the radial basis function (RBF) neural network. Simulation results obtained by the proposed method are compared with those from traditional methods. Applicability of the proposed method is verified through simulations.