An Experimental Estimation of Hybrid ANFIS-PSO-Based MPPT for PV Grid Integration under Fluctuating Sun Irradiance

Abstract

To enhance the photovoltaic (PV) power-generation conversion, maximum power point tracking (MPPT) is the foremost constituent. This article introduces an adaptive neuro-fuzzy inference system-particle swarm optimization (ANFIS-PSO)-based hybrid MPPT method to acquire rapid and maximal PV power with zero oscillation tracking. The inverter control strategy is implemented by a space vector modulation hysteresis current controller to get quality inverter current by tracking accurate reference sine-shaped current. The ANFIS-PSO-based MPPT method has no extra sensor requirement for measurement of irradiance and temperature variables. The employed methodology delivers remarkable driving control to enhance PV potential extraction. An ANFIS-PSO-controlled Zeta converter is also modeled as an impedance matching interface with zero output harmonic agreement and kept between PV modules and load regulator power circuit to perform MPPT action. The attainment of recommended hybrid ANFIS-PSO design is equated with perturb and observe, PSO, ant colony optimization, and artificial bee colony MPPT methods for the PV system. The practical validation of the proposed grid-integrated PV system is done through MATLAB interfaced dSPACE interface and the obtained responses accurately justify the proper design of control algorithms employed with superior performance.