Growing Neural Gas (GNG) based Maximum Power Point Tracking for High Performance VOC-FOC based Wind Generator System with Induction Machine

This paper presents a MPPT technique for high performance wind generator with induction machine founded on the Growing Neural Gas (GNG) network. Here a GNG network has been trained off-line to learn the turbine characteristic surface torque versus wind speed and machine speed, and implemented on-line so to perform the inversion of this function obtaining the wind free speed on the basis of the estimated torque and measured machine speed. The machine reference speed is then computed by the optimal tip speed ratio. For the experimental application, a back-to-back configuration with two voltage source converters has been considered, one on the machine side and the other on the grid side. Finally, two comparisons have been made: the first maintaining the same generator structure and comparing the GNG MMPT with the classic Perturb & Observe (P&O) MPPT, the second comparing the squirrel cage Induction Generator (IG) with a Doubly Fed Induction Generator (DFIG), both integrated with the GNG MPPT. Both comparisons have been made on real wind speed profiles.