Fully Connected Recurrent Neural Network MPPT Control Design For DFIG Wind Energy Conversion Systems

This paper presents a new maximum-power-point-tracking (MPPT) controller in wind energy conversion systems (WECS) using artificial neural networks (ANN) in order to make the wind turbine generator get the optimal efficiency from wind energy at different operating conditions. The algorithm uses fully connected recurrent neural network and is trained online using real-time recurrent learning (RTRL) algorithm. The inputs to the networks are the rotor speed and wind-turbine torque, and the output is the rotor speed command signal for the WECS. Simulation results verify the performance of the proposed algorithm.

Keywords:

doubly-fed induction generator , recurrent neural network , real-time recurrent learning , wind energy conversion systems , vector control