Maximum power point tracking based on adaptive neuro-fuzzy inference systems for a photovoltaic system with fast varying load conditions

In this paper, the adaptive neuro-fuzzy inference system (ANFIS) for solar maximum power point tracking (MPPT) has been proposed for quick and accurate tracking at different weather conditions and different load variations with high efficiency. The solar irradiance sensor does not always give accurate irradiance readings, plus the use of the sensor will be cost-effective since the PV module is influenced by the solar irradiance. This paper proposed the ANFIS-based MPPT with the elimination of the irradiance sensor. In addition to minimization of the data training, which leads to less computation burden. To enhance the response time of the system for fast varying load variations, the proposed method was combined with a constant impedance method. The proposed method is evaluated in various weather conditions. Experimental results indicate positive monitoring of the proposed method in all the different cases that were tested. A comparison of the proposed method with well-established conventional (Perturb and Observe) and soft computing-based particle swarm optimization methods have been evaluated. The results showed the superiority of the approach proposed in terms of the reduced tracking period. In addition, the proposed method provides fast convergence and obtains a steady state in less than 0.12 second.