Design and implementation of a robust ANN-PID corrector to improve high penetrations photovoltaic solar energy connected to the grid

Authors : Daouda GUEYE, Alphousseyni NDİAYE, Amadou DİAO

Pages : 121-131

Doi:10.30521/jes.1053423

View : 11 | Download : 8

Publication Date : 2023-03-31

Article Type : Research Paper

Abstract :The best quality of PV energy into the grid is now problematic that is why this paper focuses on the design and implementation of a robust Proportional Integral Derivative based on Artificial Neural Network insert ignore into journalissuearticles values(ANN-PID);. This technique used to ensure the regulation of the Boost Converter insert ignore into journalissuearticles values(BC); output voltage and the Three Phase Inverter insert ignore into journalissuearticles values(3 PI); output currents of a photovoltaic solar system insert ignore into journalissuearticles values(PVS); connected to the grid. The mathematical model of the DC bus and the 3-PI is presented. Applications under Matlab/Simulink justify the efficiency of the neural regulator. In comparison with the conventional one, the proposed method presents the best follow-up of the DC link voltage reference and a maximum overshoot of 3.16 %. In addition, despite the long time put in transient mode, the proposed method keeps better robustness and ensures an injection of current of a total harmonic distortion insert ignore into journalissuearticles values(THD); of 0.96 % against 2.18 % of the classical PID regulator.
Keywords : DC bus, PVS, Robust ANN PID, THD