Comparative Performance Evaluation of Pso-Tuned Anfis MPPT Algorithm & Ga-Tuned Anfis MPPT Algorithm for Solar Energy Conversion System

This paper introduces the development and performance evaluation of an Adaptive Neuro-Fuzzy Inference System (ANFIS) based MPPT controller designed for a DC-to-DC converter. The proposed system comprises a 2.0 kW PV array, a DC-to-DC boost converter, and a load. Leveraging the advantages of both neural and fuzzy networks, the proposed algorithm aims to optimize solar photovoltaic system parameters through the integration of an adaptive neuro-fuzzy inference system (ANFIS) controller, employing Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The comparison between PSO and GA-based optimization techniques is conducted using MATLAB/SIMULINK software, with a focus on enhancing the converter's performance. The primary objective is to determine whether the GA-tuned ANFIS MPPT algorithm outperforms in terms of tracking Maximum Power Point (MPP), tracking accuracy, and steady-state oscillation—critical parameters for solar energy conversion systems. Simulation results indicate that, across a broad range of input irradiance levels, the GA-tuned ANFIS MPPT algorithm demonstrates superior performance in tracking MPP, accuracy, and steady-state oscillation compared to the PSO-tuned ANFIS MPPT algorithm under various operating conditions.