A Neural Network based MPPT controller for variable speed Wind Energy Conversion Systems

In this paper, an Artificial Neural Network (ANN) based Maximum Power Point Tracking (MPPT) controller for Wind Energy Conversion Systems (WECS) is proposed, that achieves fast and reliable tracking of the optimum rotational speed of the turbine and accomplishes maximum power harvesting from the incident wind. The proposed control system can be implemented on any WECS and requires minimum training for the ANN as well as a small number of artificial neurons. During the training of the ANN, the WECS needs to operate simultaneously with a wind measurement system, until a sufficient amount of data is collected on all operating regions of the wind turbine and the wind turbine characteristics are determined. Next, the ANN is trained, having the rotational speed of the shaft and the power output of the generator as input signals. As a result, the wind turbine can be driven to the optimum rotor speed very fast and with high precision so as the MPPT controller can follow the fast dynamics of the wind speed. Several simulation results are presented for the validation of the effectiveness of the suggested MPPT control scheme and demonstrate the operational improvements.