This paper examines dynamic operation and control strategies for a microgrid hybrid wind-PV (photovoltaic)-FC (fuel cell) based power supply system. The system consists of the PV power, wind power, FC power, SVC (static var compensator) and an intelligent power controller. A simulation model for this hybrid energy system was developed using MATLAB/Simulink. An SVC was used to supply reactive power and regulate the voltage of the hybrid system. A GRNN (General Regression Neural Network) with an Improved PSO (Particle Swarm Optimization) algorithm, which has a non-linear characteristic, was applied to analyze the performance of the PV generation system. A high-performance on-line training RBFNSM (radial basis function network-sliding mode) algorithm was designed to derive the optimal turbine speed to extract maximum power from the wind. To achieve a fast and stable response for real power control, the intelligent controller consists of an RBFNSM and a GRNN for MPPT (maximum power point tracking) control. As a result, the validity of this paper was demonstrated through simulation of proposed algorithm. (C) 2014 Elsevier Ltd. All rights reserved.