Very-Short Term Wind Power Forecasting through Wavelet Based ANFIS

M. Nandana Jyothi (Acharya Nagarjuna University)
P.V. Ramana Rao (Acharya Nagarjuna University)

International Journal of Power Electronics and Drive Systems (IJPEDS)
Vol 9, No 1: March 2018

This paper proposes a Wavelet based Adaptive Neuro-Fuzzy Inference System (WANFIS) applied to forecast the wind power and enhance the accuracy of one step ahead with a 10 minutes resolution of real time data collected from a wind farm in North India. The proposed method consists two cases. In the first case all the inputs of wind series and output of wind power decomposition coefficients are carried out to predict the wind power. In the second case all the inputs of wind series decomposition coefficients are carried out to get wind power prediction. The performance of proposed WANFIS is compared to Wavelet Neural Network (WNN) and the results of the proposed model are shown superior to compared methods.