This study presents the development and performance analysis of an Adaptive Neuro-Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) controller for a DC-to-DC converter within a 2.0 kW PV array system. Additionally, it explores the deployment of Artificial Neural Network (ANN) based algorithms, including Levenberg-Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG), for MPPT energy harvesting in solar photovoltaic (PV) systems. The research aims to provide a comparative performance analysis of these four algorithms. A comprehensive comparison among the algorithms is conducted, focusing on their ability to handle the trained dataset, correlation between input-output, and error analysis. The study reveals that, considering the dataset training and the correlation between input-output and error, the Levenberg-Marquardt ANFIS algorithm exhibits superior performance among the tested algorithms. The MATLAB/Simulink environment is employed for designing the MPPT energy harvesting system, while the Artificial Neural Network toolbox is utilized for analyzing the developed model.