Wind power forecasting model using complex wavelet theory

Abstract

Due to growing share of wind power in world's energy consumption, forecasting of the wind power becomes essential for proper utilization. This paper proposes short term wind power forecasting model using complex wavelet transform and neural network. The past wind power values are transferred into real and complex signal; which are further transferred in Wavelet domain signal. These signals are used to predict next hour wind power using neural network. This approach is tested using data from Alberta wind farm.