Vol.:(0123456789) 1 3 Electrical Engineering https://doi.org/10.1007/s00202-021-01355-w ORIGINAL PAPER Model predictive control and ANN‑based MPPT for a multi‑level grid‑connected photovoltaic inverter Hemza Bouaouaou 1  · Djaafer Lalili 1  · Nasserdine Boudjerda 1 Received: 31 December 2020 / Accepted: 5 July 2021 © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2021 Abstract 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. Keywords Photovoltaic system · Model Predictive Control · Artificial Neural Network Control · Maximum Power Point Tracking · Five level inverter · Grid-connected inverter Abbreviations A P–n junction ideality factor, between 1 and 5 C 1234 Dc link capacitances E g Bang-gap energy of the semiconductor used in the cell e a,b,c Three phase voltages of the grid e d,q D-q components of the grid voltage i a,b,c Three phase currents of the grid i c1234 Currents in dc link capacitors i d,q D-q components of the grid current i d12345 Input currents of the five level inverter i ph Cell’s photocurrent i pv Output current of PV array i RS Cell’s reverse saturation current at reference tem- perature and solar irradiation i S Cell’s reverse saturation current I N Output current of the PV array at the Nth sample of time. I N−1 Output current of the PV array at the (N − 1)th sample of time. k Boltzman’s constant, 1.380658 × 10 –23 j/K k i Cell’s short-circuit current temperature coefficient L Line inductance of the grid N p Number of panels connected in parallel N s Number of panels connected in series q Electron charge, 1.60217733 × 10 –19 Cb q ij Switching signals of the inverter transistors R Line resistance of the grid R s Cell series resistance S Total solar irradiation, W/m 2 T c Cell’s absolute working temperature, K T ref Cell’s reference temperature, K T s Sampling time used in MPC control v c1234 Voltages of dc-link capacitors V N Output voltage of the PV array at the Nth sample of time V N−1 Output voltage of the PV array at the (N − 1)th sample of time V s Output voltage vector of the inverter v a,b,c Three phase output voltages of the inverter v dc Output voltage of PV array v d,q D-q components of the output voltage of the inverter α Scaling factor for adjusting the step size of incre- mental conductance MPPT ω Frequency of grid voltages * Djaafer Lalili djaafer.lalili@univ-jijel.dz Hemza Bouaouaou hemza_bouaouaou@univ-jijel.dz Nasserdine Boudjerda n_boudjerda@univ-jijel.dz 1 Faculty of Sciences and Technology, Renewable Energy Laboratory, Jijel University, PO Box 98, Jijel, Algeria