Adaptive Neuro-Fuzzy Inference System-Based Maximum Power Tracking Controller for Variable Speed WECS

This paper proposes an adaptive neuro-fuzzy inference system (ANFIS) maximum power point tracking (MPPT) controller for grid-connected doubly fed induction generator (DFIG)-based wind energy conversion systems (WECS). It aims at extracting maximum power from the wind by tracking the maximum power peak regardless of wind speed. The proposed MPPT controller implements an ANFIS approach with a backpropagation algorithm. The rotor speed acts as an input to the controller and torque reference as the controller's output, which further inputs the rotor side converter's speed control loop to control the rotor's actual speed by adjusting the duty ratio for the rotor side converter. The grid partition method generates input membership functions by uniformly partitioning the input variable ranges and creating a single-output Sugeno fuzzy system. The neural network trained the fuzzy input membership according to the inputs and alter the initial membership functions. The simulation results have been validated on a 2 MW wind turbine using the MATLAB/Simulink environment. The controller's performance is tested under various wind speed circumstances and compared with the performance of a conventional proportional-integral MPPT controller. The simulation study shows that WECS can operate at its optimum power for the proposed controller's wide range of input wind speed.

Automated summary

This study introduces a novel MPPT controller that maximizes wind energy extraction using a combination of neural network and fuzzy inference system, which can enhance the performance of wind energy conversion systems in different wind speed conditions.