Neural network based voltage and frequency controller for isolated wind power generation

Abstract

This paper deals with an artificial neural network based control of the voltage and frequency (VF) of autonomous wind power generation using an isolated asynchronous generator (IAG) feeding three-phase four-wire loads. The reference generator currents are estimated using the adaptive linear neuron and its training through least mean square (LMS) algorithm to control the VF of an IAG system. Three-leg voltage source converter (VSC) with an isolated T-connected transformer is used as an integrated VSC. The integrated VSC with a battery energy storage system is used to control the active power of the wind energy conversion system (WECS). Bi-directional power flow capabilities of the proposed VF controller in WECS are demonstrated through simulation results. The proposed controller functions as a VF regulator, a load leveler, a load balancer and a harmonic eliminator in the WECS. The WECS is modeled and simulated in the MATLAB using the Simulink and the sim power system toolboxes.