Neural network control of grid-connected fuel cell plants for enhancement of power quality

This paper describes the application of a solid-oxide fuel cell for compensation of distribution system voltage. A grid-connected fuel-cell plant consists of the fuel cell and the voltage-source inverter. The flux-vector control is used very effectively for the control of this inverter, where artificial neural networks implement the space-vector pulse width modulation. Comprehensive results are presented to assess the performance of this device to alleviate power quality problems present on the ac grid.