Control of Grid-tied Dual-PV LLC Converter using Adaptive Neuro Fuzzy Interface System (ANFIS)

Abstract

This paper proposes a double Maximum Power Point Tracking (MPPT) algorithm for achieving maximum efficiency of a grid-tied phase-shifted dual-PV LLC converter using the Adaptive Neuro-Fuzzy Interface System (ANFIS). The algorithm can extract maximum power from Photovoltaic (PV) panels under various weather conditions and partial shading. This dual MPPT algorithm generates switching frequency and phase shift through ANFIS to regulate the power flow using both Frequency Shift Modulation (FSM) and phase-shift modulation (PSM) techniques simultaneously. Here the ANFIS model is developed using the LLC converter’s input-output data set for each PV panel to train the neural network while the fuzzy rules ensure the optimum output using different membership functions. The second controller on the grid side maintains the DC link voltage to a fixed level as well as ensures grid power injection with minimal harmonic distortion. Derivation of this dual-MPPT algorithm and verification of the proposed closed-loop system is presented in this paper.