Donny Radianto, Masahito Shoyama
In this paper, A two-phase interleaved boost converter (IBC), which is based on Adaptive Neuro-Fuzzy Inference System (ANFIS) for photovoltaic (PV) system is proposed. The proposed system has two inputs and 1 output. Two inputs of the proposed system consist of solar irradiation and temperature. Meanwhile, the output of the proposed system is aduty cycle. The duty cycle is used to generate Pulsed Width Modulation (PWM), which serves to activate MOSFET. Furthermore, the proposed ANFIS features 20 epochs and utilizes hybrid mechanism to train data. Some simulations of IBC combined with PV system have been performed using Matlab / SIMULINK. Furthermore, some comparisons of two different methods have been carried out to validate the results. The comparison analysis results indicate that the system using ANFIS can obtain higher voltage than the system using FLC. In addition, the proposed system is also able to reduce overshoot and be able to increase the output power. © 2014 IEEE.
Department of Electrical Engineering, Kyushu University, Japan; State Polytechnic of Malang, Indonesia