Performance evaluation of ANN and ANFIS based wind speed sensor-less MPPT controller

Abstract

Two artificial intelligence (AI) techniques, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS), have been proposed for maximum power point tracking (MPPT) of wind energy systems. Both the ANN and ANFIS based controllers have the ability to track the maximum power point (MPP) and the corresponding rotor speed of the wind generator by estimating wind speed with very little error. The ANN network utilizes feed forward back-propagation algorithm to train the network during the learning process, and uses gradient-decent search technique to adjust the weights between nodes to minimize the error. On the other hand, the ANFIS network combines the artificial neural network with the fuzzy decision process, making it more efficient. Neither of the algorithms requires any mechanical sensor for wind speed measurement. From the simulation results, it has been observed that the ANN as well as ANFIS methods are suitable for estimating wind speed and tracking the maximum power point and the corresponding rotor speed. ANFIS based controller, however, is more accurate and robust compared to the ANN based one in terms of wind speed estimation. Similar performances have also been noticed in the determination of maximum power and rotor speed.