African vulture optimized RNN algorithm maximum power point tracking (MPPT) controller for photovoltaic (PV) system

Normally, the solar photovoltaic system, the stand-alone or grid-connected system delivers power; it has a photovoltaic panel, a DC-DC converter, and a load consist. A fast and efficient MPPT method is required to track maximum power from photovoltaic panels and DC-DC converters under varying temperatures and irradiance. This study presents a smart controller-established MPPT procedure for a separate photovoltaic structure to trace the maximum power. A meta-heuristic African vulture optimized recurrent neural network (AVO-RNN) is proposed to remove the extreme power as of presented solar vitality for a 3-phase shunt Active Power Filter (APF) grid-linked PV structure. To enhance MPP tracking in photovoltaic arrays a hybrid technique is proposed. It addresses the limitations of traditional methods under varying irradiation by incorporating both current and voltage from the photovoltaic array with the duty cycle of the DC-DC Boost converter as the output constraint. The suggested method reduced as AVOA-RNN MPPT controller established on the African vulture optimization (AVO) algorithm that is beneficial to train the established RNN and to change the joining weights and preferences to get the optimum ideals of duty-cycle converter conforming to the maximum power point of a photovoltaic array. To address grid requirements a 3-phase shunt active power filter (SAPF) is utilized. The proposed MPPT algorithm is validated with MATLAB. The proposed hybrid AVOA-RNN technique achieves an overall accuracy of 99.81 % than existing hybrid PSO-RNN, conventional INC, SSA-GWO, and FO-INC techniques of 93.11 %, 94.42 %, 96.75 % and 98.12 % respectively.