Rajab Al-Jaboury, Omar N.Hamodat, ZaidDaoud, Raid W.2024-05-312024-05-312024Rajab Al-Jaboury, O. N., Hamodat, Z., Daoud, R. W. (2024). Design of power control circuit for grid-connected PV system-based neural network. Journal of Robotics and Control (JRC), 5(3), 821-828. 10.18196/jrc.v5i3.207512715-5056https://hdl.handle.net/20.500.12939/4715This research explores the application of neural networks in managing grid- photovoltaic (PV) systems. this paper aims to improve the performance and reliability of PV systems using artificial intelligence capabilities, specifically neural networks. The main emphasis of this system is to control active and reactive power and to track the maximum power point (MPPT). This study introduces an intelligent control technique for fuel cell distributed generation (DG) grid connection inverters. The algorithm allows for the management of both active and reactive power for the unit. The algorithm provides local reactive power compensation, making it economically viable. The controller modeling and performance validation are conducted using MATLAB/Simulink and Sim power system blocks, demonstrating its capacity for enhancing power factor. This makes fuel cell technology a clean, highly controllable, and economically viable option for DG systems. The system maximizes the energy extraction of PV panels and maintains them at their ideal PowerPoint across various environmental conditions. It also raises the voltage from 260 volts to 350 volts. Simulations and practical evaluations validate the proposed control system. The obtained results indicate that the total harmonic distortion (THD) of the grid current under operating conditions was less than 1.86%. This demonstrates significant improvements in the efficiency and reliability of PV systems. The neural network controller shows remarkable flexibility and the ability to quickly adapt to fluctuations in load and radiation, which contributes to developing a more sustainable and stable energy network.eninfo:eu-repo/semantics/closedAccessGrid Active Power ControlMaximum Power Point Tracking (MPPT)Neural NetworksPVReactive Power ControlArticle538218282-s2.0-85193775795Q2