New improved hybrid MPPT based on neural network-model predictive control-kalman filter for photovoltaic system

Nora Kacimi (National Polytechnic School)
Said Grouni (University M’Hamed Bougara of Boumerdes)
Abdelhakim Idir (University Mohamed Boudiaf of M'sila)
Mohamed Seghir Boucherit (National Polytechnic School)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 20, No 3: December 2020

In this paper, new hybrid maximum power point tracking (MPPT) strategy for Photovoltaic Systems has been proposed. The proposed technique for MPPT control based on a novel combination of an artificial neural network (ANN) with an improved model predictive control using kalman filter (NN-MPC-KF). In this paper the Kalman filter is used to estimate the converter state vector for minimized the cost function then predict the future value to track the maximum power point (MPP) with fast changing weather parameters. The proposed control technique can track the MPP in fast changing irradiance conditions and a small overshoot. Finally, the system is simulated in the MATLAB/Simulink environment. Several tests under stable and variable environmental conditions are made for the four algorithms, and results show a better performance of the proposed MPPT compared to conventional Perturb and Observation (P&O), neural network based proprtional integral control (NN-PI) and Neural Network based model predictive control (NN-MPC) in terms of response time, efficiency and steady-state oscillations.