Sensorless Power Maximization of PMSG Based Isolated Wind-Battery Hybrid System Using Adaptive Neuro-Fuzzy Controller

Abstract

This paper presents a novel Adaptive Network-Based Fuzzy Inference System(ANFIS) for the optimal control of permanent magnet synchronous generator (PMSG) to extract maximum power without the need of speed & position sensors or any complex estimating algorithm. The control algorithm determines the optimal value of torque controlling current component as a function of change in output power. The error between the optimal values of torque current and actual current is utilized to train the ANFIS structure using error back propagation method. In the proposed work, an isolated wind-battery hybrid system is considered, where a boost chopper is used to control the PMSG. A buck-boost converter is used to maintain constant DC-Link voltage and to interface an efficient battery energy storage system (BESS) in order to meet fluctuating load demand under varying wind conditions. The proposed strategy is realized and simulated in MATLAB/SPS environment. The simulation results under dynamic operating conditions are provided to demonstrate the effectiveness of proposed strategy.