Model predictive control and ANN-based MPPT for a multi-level grid-connected photovoltaic inverter

This paper deals with the control of a five-level grid-connected photovoltaic inverter. Model Predictive Control is applied for controlling active and reactive powers injected into the grid. The operation of the photovoltaic field at the maximum power point is ensured using an algorithm based on a neural network. Model Predictive Control is based on the choice of inverter state by minimizing a cost function that depends on active and reactive powers. In addition, the redundant states of the inverter are directly utilized to balance the bus voltages of the inverter, making overall system control simple and efficient.